diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..857b7b8c6340776b00db0f97db2706645c7ccd87
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..1107ac71eb362a9713c4018ad66aacea3ab74b0a
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_50/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..2c1b07afd7a3663e23e25823089a76a1493561a2
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_60/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..aeeed12d0b1d0d53e87645784baf603b6795f74b
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_70/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d133eefde51650e7ff4fdf11a19a713081b87eb0
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_97/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d64f27ca41bd5e26b666fdba3513ecd5dcc21888
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_30/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5dcd6ed0b0e52dbbfcfada12f15445f55dbe8aa
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_40/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..e37138f3cd5d71ab5a137dbf18614f6810d5025e
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k/global_step_48/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..7d029d711c2851988f5bb1266881a9b55d4e9816
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_70/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4207cde02be063221c81248e60494de9ca8acb2
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_80/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..bed6a9dc3a5ed72fa967bfe2c53907775f38bac5
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_90/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..f69b702dce17aa2ce769237a1cea084b4c156101
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_30_multimath_rl_50k/global_step_97/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d49a18c0c04d7b9153d67684dbc471bc43d0c943
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_60/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..85f36f2e673cfe89672e4b2388adf870fff1f4ff
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00003-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00003-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00003-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00003.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00003-of-00003.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00003.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00003.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00003.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_70/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ce1b4b7fbea6e1fea8422b3ba1e70f86b15c83d
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_80/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..346af78e913141aae4e799851994a9988d25150e
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_90/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..53f75697aabf5b9aa20c43808a45cb8f3bf026d7
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_25k_global_step_40_multimath_rl_50k/global_step_97/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..f94ab7a13b71f12ce747a4b70e53ab71ff3c0afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00003.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00003.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00003.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00003.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00003.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00003.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00003.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00003.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00003.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_100/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd373bf0f0841e5961e9af65d6a2db78d90b81af
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_50/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef278d8aade3d9c12c35987d4deca2c4e297638e
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_60/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d80c2d05cb359cec3d05797508c96780e0a133ce
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_70/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..01a42d0199ca8b23264aa6cd18cf0d211a3a0eaa
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_80/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..8f2cbeafee108a78389c138567479005f36430ca
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k/global_step_90/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..50a926b6f830fcdf7d1d8d185df2d9d3a44fd46e
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_10/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 151643,
+ "do_sample": true,
+ "eos_token_id": [
+ 151645,
+ 151643
+ ],
+ "pad_token_id": 151643,
+ "temperature": 0.7,
+ "top_k": 20,
+ "top_p": 0.8,
+ "transformers_version": "5.0.0.dev0"
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..91ddf5ad368a979ebc2f9951be9397c4b5c9c25b
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/model.safetensors.index.json
@@ -0,0 +1,722 @@
+{
+ "metadata": {
+ "total_parameters": 4826771968,
+ "total_size": 9653543936
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/processor_config.json
@@ -0,0 +1,85 @@
+{
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_pixels": null,
+ "merge_size": 2,
+ "min_pixels": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "device": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "input_data_format": null,
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "num_frames": null,
+ "pad_size": null,
+ "patch_size": 16,
+ "processor_class": "Qwen3VLProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_metadata": null,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_20/tokenizer_config.json
@@ -0,0 +1,240 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151665": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151666": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151667": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151668": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "extra_special_tokens": {},
+ "model_max_length": 262144,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/added_tokens.json
@@ -0,0 +1,28 @@
+{
+ "": 151668,
+ "": 151658,
+ "": 151666,
+ "": 151667,
+ "": 151657,
+ "": 151665,
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|file_sep|>": 151664,
+ "<|fim_middle|>": 151660,
+ "<|fim_pad|>": 151662,
+ "<|fim_prefix|>": 151659,
+ "<|fim_suffix|>": 151661,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|repo_name|>": 151663,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/chat_template.jinja
@@ -0,0 +1,120 @@
+{%- if tools %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].role == 'system' %}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- endfor %}
+ {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {{- '<|im_start|>system\n' }}
+ {%- if messages[0].content is string %}
+ {{- messages[0].content }}
+ {%- else %}
+ {%- for content in messages[0].content %}
+ {%- if 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+ {%- if message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role + '\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content_item in message.content %}
+ {%- if 'text' in content_item %}
+ {{- content_item.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {%- if message.tool_calls %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if (loop.first and message.content) or (not loop.first) %}
+ {{- '\n' }}
+ {%- endif %}
+ {%- if tool_call.function %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n{"name": "' }}
+ {{- tool_call.name }}
+ {{- '", "arguments": ' }}
+ {%- if tool_call.arguments is string %}
+ {{- tool_call.arguments }}
+ {%- else %}
+ {{- tool_call.arguments | tojson }}
+ {%- endif %}
+ {{- '}\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {%- if message.content is string %}
+ {{- message.content }}
+ {%- else %}
+ {%- for content in message.content %}
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+ <|vision_start|><|image_pad|><|vision_end|>
+ {%- elif content.type == 'video' or 'video' in content %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+ <|vision_start|><|video_pad|><|vision_end|>
+ {%- elif 'text' in content %}
+ {{- content.text }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd
--- /dev/null
+++ b/posttrain_models/qwen3vl_4b_ntr_multimath_gemini_50k_global_step_100_multimath_rl_50k/global_step_30/config.json
@@ -0,0 +1,68 @@
+{
+ "architectures": [
+ "Qwen3VLForConditionalGeneration"
+ ],
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "image_token_id": 151655,
+ "model_type": "qwen3_vl",
+ "pad_token_id": 151643,
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "dtype": "float32",
+ "eos_token_id": 151645,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.02,
+ "intermediate_size": 9728,
+ "max_position_embeddings": 262144,
+ "model_type": "qwen3_vl_text",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 36,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 5000000,
+ "tie_word_embeddings": true,
+ "use_cache": true,
+ "vocab_size": 151936,
+ "rope_scaling": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 24,
+ 20,
+ 20
+ ],
+ "rope_theta": 5000000,
+ "rope_type": "default"
+ }
+ },
+ "tie_word_embeddings": true,
+ "transformers_version": "5.0.0.dev0",
+ "video_token_id": 151656,
+ "vision_config": {
+ "deepstack_visual_indexes": [
+ 5,
+ 11,
+ 17
+ ],
+ "depth": 24,
+ "dtype": "float32",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1024,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "model_type": "qwen3_vl",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 2560,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652
+}
\ No newline at end of file