diff --git a/.gitattributes b/.gitattributes index 24a9787989594e1a9b424f9eb8901af878d5c05e..202c1045a3ee106555af6f77eee06e8719d77af0 100644 --- a/.gitattributes +++ b/.gitattributes @@ -86,3 +86,4 @@ g2_6_oldcode_review_newcode_v4/pre-anneal/500M/tokenizer.json filter=lfs diff=lf g2_5_plan_newcode__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text g2_6_oldcode_review_newcode_v4__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text +g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/chat_template.jinja b/g1_0_baseline_original_code__edit/pre-anneal/500M/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bc04d07ecd954b15ef549f71de64c11e59c813cc --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/chat_template.jinja @@ -0,0 +1 @@ +{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/config.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/config.json new file mode 100644 index 0000000000000000000000000000000000000000..221b35732eb29193e109e079805f05cc9a2d9d8d --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/config.json @@ -0,0 +1,178 @@ +{ + "architectures": [ + "Gemma4ForConditionalGeneration" + ], + "audio_config": null, + "audio_token_id": 258881, + "boa_token_id": 256000, + "boi_token_id": 255999, + "bos_token_id": 2, + "dtype": "bfloat16", + "eoa_token_id": 258883, + "eoa_token_index": 258883, + "eoi_token_id": 258882, + "eos_token_id": 1, + "hidden_size": 5376, + "image_token_id": 258880, + "initializer_range": 0.02, + "model_type": "gemma4", + "pad_token_id": 0, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attention_k_eq_v": true, + "bos_token_id": 2, + "dtype": "bfloat16", + "enable_moe_block": false, + "eos_token_id": 1, + "expert_intermediate_size": null, + "final_logit_softcapping": 30.0, + "global_head_dim": 512, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 5376, + "hidden_size_per_layer_input": 0, + "initializer_range": 0.02, + "intermediate_size": 21504, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 262144, + "model_type": "gemma4_text", + "moe_intermediate_size": null, + "num_attention_heads": 32, + "num_experts": null, + "num_global_key_value_heads": 4, + "num_hidden_layers": 60, + "num_key_value_heads": 16, + "num_kv_shared_layers": 0, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "partial_rotary_factor": 0.25, + "rope_theta": 1000000.0, + "rope_type": "proportional" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 1024, + "tie_word_embeddings": true, + "top_k_experts": null, + "use_bidirectional_attention": "vision", + "use_cache": false, + "use_double_wide_mlp": false, + "vocab_size": 262144, + "vocab_size_per_layer_input": 262144 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.0", + "use_cache": false, + "video_token_id": 258884, + "vision_config": { + "_name_or_path": "", + "architectures": null, + "attention_bias": false, + "attention_dropout": 0.0, + "chunk_size_feed_forward": 0, + "default_output_length": 280, + "dtype": "bfloat16", + "global_head_dim": 72, + "head_dim": 72, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 1152, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_range": 0.02, + "intermediate_size": 4304, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "max_position_embeddings": 131072, + "model_type": "gemma4_vision", + "num_attention_heads": 16, + "num_hidden_layers": 27, + "num_key_value_heads": 16, + "output_attentions": false, + "output_hidden_states": false, + "patch_size": 16, + "pooling_kernel_size": 3, + "position_embedding_size": 10240, + "problem_type": null, + "return_dict": true, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 100.0, + "rope_type": "default" + }, + "standardize": true, + "use_clipped_linears": false + }, + "vision_soft_tokens_per_image": 280 +} diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/generation_config.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..97148f0fb448d506cf74a93f48459e63f811ad27 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 2, + "do_sample": true, + "eos_token_id": [ + 1, + 1 + ], + "pad_token_id": 0, + "temperature": 1.0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.10.0" +} diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/latest b/g1_0_baseline_original_code__edit/pre-anneal/500M/latest new file mode 100644 index 0000000000000000000000000000000000000000..7cb7374b21fd322c33b2aed487af4a75e2644bec --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/latest @@ -0,0 +1 @@ +global_step636 \ No newline at end of file diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/model-00001-of-00002.safetensors b/g1_0_baseline_original_code__edit/pre-anneal/500M/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ef1a5cd2a423c56baa520888bc6e6054fec8cfa --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4ff7e61c76864e4f4640b5499f38e14cd8ed87dd674035bef7d3cab42104847 +size 49923154850 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/model-00002-of-00002.safetensors b/g1_0_baseline_original_code__edit/pre-anneal/500M/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45c58943fc93b21c37b1e61a26b6677a30d64ff6 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469465d56e9e7364eccb473f676426e5a3141f5fdf45a7d66f39aa435698236c +size 12623183414 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/model.safetensors.index.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..2b4e4c88f908a51891994c9e315db28e438ce22f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/model.safetensors.index.json @@ -0,0 +1,1196 @@ +{ + "metadata": { + "total_parameters": 1459760, + "total_size": 62546177752 + }, + "weight_map": { + "model.embed_vision.embedding_projection.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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.pre_feedforward_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-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-00001-of-00002.safetensors", + "model.language_model.layers.10.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.pre_feedforward_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-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.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.pre_feedforward_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-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.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.pre_feedforward_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.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.24.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.30.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.33.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.pre_feedforward_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-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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.pre_feedforward_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.36.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.layer_scalar": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.49.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.layer_scalar": "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-00001-of-00002.safetensors", + "model.language_model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.pre_feedforward_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.50.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.layer_scalar": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.59.self_attn.q_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.pre_feedforward_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.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.layer_scalar": "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.pre_feedforward_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-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.mlp.down_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.mlp.up_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.patch_embedder.input_proj.weight": "model-00002-of-00002.safetensors", + "model.vision_tower.patch_embedder.position_embedding_table": "model-00002-of-00002.safetensors", + "model.vision_tower.std_bias": "model-00002-of-00002.safetensors", + "model.vision_tower.std_scale": "model-00002-of-00002.safetensors" + } +} diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/processor_config.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5465974d23e1eca2c46c2809b26c997946ce0d90 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/processor_config.json @@ -0,0 +1,75 @@ +{ + "audio_ms_per_token": 40, + "audio_seq_length": 750, + "feature_extractor": { + "dither": 0.0, + "feature_extractor_type": "Gemma4AudioFeatureExtractor", + "feature_size": 128, + "fft_length": 512, + "fft_overdrive": false, + "frame_length": 320, + "hop_length": 160, + "input_scale_factor": 1.0, + "max_frequency": 8000.0, + "mel_floor": 0.001, + "min_frequency": 0.0, + "padding_side": "right", + "padding_value": 0.0, + "per_bin_mean": null, + "per_bin_stddev": null, + "preemphasis": 0.0, + "preemphasis_htk_flavor": true, + "return_attention_mask": true, + "sampling_rate": 16000 + }, + "image_processor": { + "do_convert_rgb": true, + "do_normalize": false, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.0, + 0.0, + 0.0 + ], + "image_processor_type": "Gemma4ImageProcessor", + "image_seq_length": 280, + "image_std": [ + 1.0, + 1.0, + 1.0 + ], + "max_soft_tokens": 280, + "patch_size": 16, + "pooling_kernel_size": 3, + "resample": 3, + "rescale_factor": 0.00392156862745098 + }, + "image_seq_length": 280, + "processor_class": "Gemma4Processor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "image_mean": [ + 0.0, + 0.0, + 0.0 + ], + "image_std": [ + 1.0, + 1.0, + 1.0 + ], + "max_soft_tokens": 70, + "num_frames": 32, + "patch_size": 16, + "pooling_kernel_size": 3, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "video_processor_type": "Gemma4VideoProcessor" + } +} diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_0.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c56fc4a93e82e8480e2453edd8f678f741a3d61 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d7dcf54a8dbd1fff243640ddc034149fbe7c90ed70b8a95a6bb093e989a7577 +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_1.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f2e938c0928f813d10b4e55bb2212d3ef91aca8a --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a2b0b9d330140afd742a57df45106276d425d38a78e53b0fd43dba9559f8d4 +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_10.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_10.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdb54fd629df1da3ab81c494002d6b26cfb4a97d --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_10.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce222f8f11fd62fd6cb82264500aefbc9e7ef16907ed3e4aa3a8a99c21d95d3 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_11.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_11.pth new file mode 100644 index 0000000000000000000000000000000000000000..024e08f772087cbaf09146b2774e3a02309c478f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_11.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07144bfc4ed675dda70ab66923d17d6f9233560b2db09689cbe1f262c590c88 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_12.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_12.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f7a50d0e4c59bfab5b42ce72c9ca34d7d029d10 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_12.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e08d78f1863585829c3beb514b0be2b6dd5058d44950b2f5529180ed3bf200 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_13.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_13.pth new file mode 100644 index 0000000000000000000000000000000000000000..9da259c78b343e76598a5bceb632975342b89438 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_13.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd02cc08e60bd490e7809bb22626bbc382309e0548b8d176712a72282b79bc7 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_14.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_14.pth new file mode 100644 index 0000000000000000000000000000000000000000..f95ff963ac8489c474c4393654abacdf9a909674 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_14.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d37c4ee644f088f47b9557f56e86307d31179db8414f7bddc801e9db40814e +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_15.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_15.pth new file mode 100644 index 0000000000000000000000000000000000000000..38cbc708356567366a556b88c20ead8ebec0e209 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_15.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61612e6aea130f0a379adbe720ad1b2bf382caaf91aaabbe6692f9b6842cfd7 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_16.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_16.pth new file mode 100644 index 0000000000000000000000000000000000000000..387539fe93c71666582cedf5cc7f28d96aa4c869 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_16.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048535719240855c8721c08701459b3772c42c064b43cefb8c0859c8c8847bfb +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_17.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_17.pth new file mode 100644 index 0000000000000000000000000000000000000000..87d2a7295c6558a32eaade05df59a693d4e2127d --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_17.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b381294da5be4f5d6c1fff6daed9292ef379337e249c8925ef46b492ef3ee310 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_18.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_18.pth new file mode 100644 index 0000000000000000000000000000000000000000..271fd8a0fad11dc06890d33e1f7876eaa4180f7f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_18.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebc632331f136fb796e109f7d0378641d1e5aadd801c90aff7d8bf2598d0e13 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_19.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_19.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ce815bbaf625a61f1b3a664a270ebe87ac0b7f6 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_19.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbbbc31fd3a5dc41a109296b8e8462fa1e9a5f271dff0ac41dd90f8e4d2d7c36 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_2.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9a5e8dd1afbdab70c58d1a389c8652878003b05 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5db634f6ed5151d3c898fbe3c365f950516c404bed926de16b253b26e63c7cf +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_20.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_20.pth new file mode 100644 index 0000000000000000000000000000000000000000..357e7dabdad57273ccd2a6dd6eec68a8664f1ae4 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_20.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e0128907c3a7a5f8d28de699f336992dcbbe4936f86e3a5ee90f2dec42e79f +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_21.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_21.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d9f3bc325c12b6d8836d4c9faca755862fcdef4 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_21.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22597879b2fe99eba1397996a6ccc3e1ef32321f02c63d8158971b41a70fb8e8 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_22.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_22.pth new file mode 100644 index 0000000000000000000000000000000000000000..5619b87ba040bb80fccfb7efc1d76c0e13536b1f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_22.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c34c34cb1f037aabc2706908c5d7212ed45922130afce933667e1454b6f034 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_23.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_23.pth new file mode 100644 index 0000000000000000000000000000000000000000..d21aa9e79752d0c210a91b0346778297dcc9a7af --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_23.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9269652b84f705adc87d3a16df047010fb3fa29b11349033478b4776d15f0e32 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_24.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_24.pth new file mode 100644 index 0000000000000000000000000000000000000000..37efe8ff0062d2f0b2f3877f9f9b455640ecb0de --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_24.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9e6a074c879eb7683ab1cca4f686aab7505f734596e8bf42e3582aff414cc5 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_25.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_25.pth new file mode 100644 index 0000000000000000000000000000000000000000..e1bbb9fc24d48a5c9e2e1898352744e231b57854 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_25.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:addb12b2fe7960526e1e7786804e1359c161bb40e8c305f708dc0cc14061bff2 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_26.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_26.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbb22b4f50042a7d3eb8d0d63f807f07c41dbc24 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_26.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c744753a5acb3e37d956b8f7eb68d2cca0f195c1d0389c146cc8e2d00736bb4 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_27.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_27.pth new file mode 100644 index 0000000000000000000000000000000000000000..125b78ce53391fcea3a802272622656fd7183291 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_27.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b586c343d320258372038d4d211ed449c11517e9f5e1c5fcb76bfc7a74687fb +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_28.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_28.pth new file mode 100644 index 0000000000000000000000000000000000000000..d49edc9f606873fa9a8ee8aaaa8b15f8e7399571 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_28.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b46e1a86fdd08125a5abc42a2d4618d55acd88300e9cf35abb586e4d534eea9 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_29.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_29.pth new file mode 100644 index 0000000000000000000000000000000000000000..7712d457ced23105774aead76109dcf3f00a407a --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_29.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef12a2de484b1fb274fd5576d9ac18c80f0659ad29a92c43d8e90fdd70a7734f +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_3.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..33bcfdb6b6522f9905e2cfcadd47315486252b49 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad774eade44525098fff2d5910e3d16565fca4c2af29ed0bc4d9315a8ac9607a +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_30.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_30.pth new file mode 100644 index 0000000000000000000000000000000000000000..79348919971e663ee09484fcadddaa5d86efe2c5 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_30.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5a64f55f5b524c1d45986d113944687207fd40932aa517c50ac25554d380cb +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_31.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_31.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3269688769e76e9cd956a106f337611de124244 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_31.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c2549059d0e017510a8912ae3114b8312b83d6a0cecc341356570eb3bbbe66 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_32.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_32.pth new file mode 100644 index 0000000000000000000000000000000000000000..c267f9e1cc40859743bb63c946ac069d7282e934 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_32.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7879edbf3c49cb48dbb9dd713c7c546507031ed29db3b17a4e0566464395b40 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_33.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_33.pth new file mode 100644 index 0000000000000000000000000000000000000000..4636f4c31a6c125bdabf861797fe44296e023123 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_33.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72e27887b2cd13b128841aff5988a61d290f09a99374194b72d970e50b061a9 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_34.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_34.pth new file mode 100644 index 0000000000000000000000000000000000000000..ffb8514fb012dae603591537dc484647f85f9540 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_34.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb31c31655e2888adededf783d31f622880ad5d94d3482d6513222056b02afee +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_35.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_35.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e4fc7c1a2e77116f8f632263377b713611a2e49 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_35.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fbefc809d13afc0266f26eee722ed2215ccbf20ea993393930075bc8e755758 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_36.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_36.pth new file mode 100644 index 0000000000000000000000000000000000000000..80a778e8f1c149699e22ec80cf232b1e55b75fb5 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_36.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c94c0223ead01438d94c0512a52285243eae170c3762b1074dc3d903e6695cc +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_37.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_37.pth new file mode 100644 index 0000000000000000000000000000000000000000..a59b98acd0d8d6d18c6131c907ab3ff5a744f4eb --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_37.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b9758407564a28dadafc20701dfacd7e5a298a669158c72a1dbd5bf49ecbca +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_38.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_38.pth new file mode 100644 index 0000000000000000000000000000000000000000..57e12ff0b8c1b94d496cef9e4720dc76aca2e97a --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_38.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77138dd39b3982453c2e48495f87c54612996f42f004a82b51d977de9b594c20 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_39.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_39.pth new file mode 100644 index 0000000000000000000000000000000000000000..ebea2694fc1df84e268cc8652667539cfce1bb52 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_39.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fc0038ae4a11c965bc71937b7211bdf963b37b588f440aa7bf0bf1b41d8e89 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_4.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..fb8c53a2cdf8b7fec0071e6a7c512ad93a180ac6 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdee1b37be2238764bcfeed9dad268e938248152b0fba60eaf89adda99eac0f +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_40.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_40.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab1ffc941c76919a13b71ffe2688094722562af5 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_40.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2b4624c04df7281c4f6a2322c5590dd34e8e99bf279eb95068c2a044bacbdb +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_41.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_41.pth new file mode 100644 index 0000000000000000000000000000000000000000..79a90bb98f5e177d0b75e6ba1aa88f4d6f46f3ac --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_41.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccb0c6a383aa75920dc3d0dd931477746e472d1dfc8bed5d67053d53cc50cbf +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_42.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_42.pth new file mode 100644 index 0000000000000000000000000000000000000000..f897d3ae90e51a0f722067e57b51bc9bb55f7b33 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_42.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:526e100a2d0659e72a19bb503ea5a1ea901df362ae751f70ee167c8bacb755ae +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_43.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_43.pth new file mode 100644 index 0000000000000000000000000000000000000000..deba13bad21a8e74968dc249b449524d3f02ecff --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_43.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3049597adee88bd5adaae1a41905e21082bdcc322e02b9b49658766371dcd567 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_44.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_44.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9f7575f5b5d378626dd210435ab64c39d6482c1 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_44.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b20c147d255aee4a21cc00ce71f9395c14749ba61cd83fa0f8eb2b5efa380a +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_45.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_45.pth new file mode 100644 index 0000000000000000000000000000000000000000..f78de48871cda49b0e4bf5923e3cd450a8667a86 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_45.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b12c2ace72a2f50d02eca5766de8929307316f6416cd40e9094152c62d12542 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_46.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_46.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f3773eb543515490bca052cb00c3930f743ea11 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_46.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ee09bf565ec6ad71842436a2a60730b37dd465948e5236166ba9cf7a795cfe +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_47.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_47.pth new file mode 100644 index 0000000000000000000000000000000000000000..d319921b4556f6af0fa0b7e34b721424ca04b407 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_47.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1516108fa7cd8e17241ff69f465315954d0b73eba51a9d1f2bda489d4b53450 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_48.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_48.pth new file mode 100644 index 0000000000000000000000000000000000000000..d88d146865f1417a15c3056d06df98897381ad3b --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_48.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d10c2b5eac2a47cdee95f8fb7e0124322ef0ae885bcf5357dbc5f6a28b5dc18d +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_49.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_49.pth new file mode 100644 index 0000000000000000000000000000000000000000..df6f89d00c1bd815a58d11362ace2faf821b8d54 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_49.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c3ceb2aacac967bc32a82aee35f115a42fed7a205436c3be1876ffde064c34 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_5.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f65e37ec643889eba376fdae32e98ce94abf64e --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6046157bd3d69a7cf6ee508b7359b30cb71488a11b11b07a614041b06813c553 +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_50.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_50.pth new file mode 100644 index 0000000000000000000000000000000000000000..d13851cf380a11ecca3a0b8fabf36359e01b8a6e --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_50.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a38a194be832049df69a471788d56240d6ba2fc8f704e1795b9e8bbbfdcc37f +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_51.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_51.pth new file mode 100644 index 0000000000000000000000000000000000000000..4eb056c71c404a7185e690f324d73abdeca219b9 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_51.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50cd60964c2a2d5889faf962a03e6aaddf9118c8b51e8f7852a276c4029a89ac +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_52.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_52.pth new file mode 100644 index 0000000000000000000000000000000000000000..05d2bc69d33c89d67f16d0e705c47949d4f84c82 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_52.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b39abc92527a83400dae10f3e6ea7a1a0db0b3f939ea1233acb5ca59da012e +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_53.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_53.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fc9023dc77aa2a560110424512d50c17957717b --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_53.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f35fba7c690842b68cc71489dc8e3eb3518bf017811835a7bdf12955e0ffc26 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_54.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_54.pth new file mode 100644 index 0000000000000000000000000000000000000000..961a4a947f72789ee437f4f433541fb1a4cd270c --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_54.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39a60fbed62ecca5470c80d88d331e35de24226a8da555ed8d3d5047397a024b +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_55.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_55.pth new file mode 100644 index 0000000000000000000000000000000000000000..14e73837a0f04130e4c7a2039c665a48bac41286 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_55.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b8c8e05986c2f4e96fa1985ab1dfc4b662bfc8e3b7c925585ef604ce6ca751 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_56.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_56.pth new file mode 100644 index 0000000000000000000000000000000000000000..e837c076cd8e5cd4c693a553eff80357ab48b598 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_56.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4f031c572be38bd3f151fc632204237e588b957e512913a76a447c6f5ee770 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_57.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_57.pth new file mode 100644 index 0000000000000000000000000000000000000000..61e13531dc5526d52583deee300ef1b8c55e8154 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_57.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccaf0628a1163c7a1a20c67f0d30b6152b6a2578599967e70c8ed587cd11c45b +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_58.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_58.pth new file mode 100644 index 0000000000000000000000000000000000000000..f46db4e577d6ea8a2b8d1a64d7ac61e8f30bb76f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_58.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c6e1a6989ee9845b1e456197e44d4c477ab9036394ea2f80afbab6df11a15c +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_59.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_59.pth new file mode 100644 index 0000000000000000000000000000000000000000..4f5be28104839c6f7efd9e5e1c68ac144640afba --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_59.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc6b4f24bd4bf1aec4b9f10a79452e35239ad45af443405ced8a838ce55aaf1 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_6.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1f63654cc6425836bdbfa5770e7904635945beb --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc9300f101a324d0361f01aec1d57e26b57a703b4e536f4fe982c8ba57a9144 +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_60.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_60.pth new file mode 100644 index 0000000000000000000000000000000000000000..839c80f464c5cc9336c6e1f293060aaccc2aeef9 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_60.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cef76d50b7d4a2e0a38f30e68fd8cc6295f0f3fa99a2a9c0eed2e468c0511d +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_61.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_61.pth new file mode 100644 index 0000000000000000000000000000000000000000..a501916120299f16882e16b2159876a5a6509277 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_61.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce5e4e9981c26fd6be59a29e5b7fc3a11d98b40592d7e1255c308e6b00946742 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_62.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_62.pth new file mode 100644 index 0000000000000000000000000000000000000000..a327a8de10d0ee6a6a44d2fedc2bf2412d4ecbe6 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_62.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2f28a40c6fe9bddc699822139459cc5487c7ce38c590761795d15962b36c62 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_63.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_63.pth new file mode 100644 index 0000000000000000000000000000000000000000..de797180c786bbb03afbec134989a2eec4adfe30 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_63.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae6acbb146ff8d2c5326cacde689c4696bb0b35d0a31608a34eaadbc6889fcc +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_64.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_64.pth new file mode 100644 index 0000000000000000000000000000000000000000..1cd632374806fcae37217f97c4525ec1cc6e41b3 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_64.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53101857e3a1486ae062b9ffdee08ac760cef82946b16fab2fbd815aca6d0d3a +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_65.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_65.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6a6183ec72a38e3519af2e2d0e0798121b26286 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_65.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899ee6be42d14e6f008e388250d4d2ab1dddb210ecd18ba8b7c36a2416dc9696 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_66.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_66.pth new file mode 100644 index 0000000000000000000000000000000000000000..7df67afee76fffceee9317fa6986bfc60640c511 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_66.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4849284c768715c7818deb256a820aafcb55110c7950635fbfaf33f311afd5f6 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_67.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_67.pth new file mode 100644 index 0000000000000000000000000000000000000000..67a9152195bd5a75ccdae1c17d2b602e34643843 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_67.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495cc24237ee847cb964b4ac9bf51abab7e44591ec3b15f5a3b08ed4374286cd +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_68.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_68.pth new file mode 100644 index 0000000000000000000000000000000000000000..24fe2f1bcaca28f99769119a1466dd2317b47d02 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_68.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef3d8edf5f3904795b0254221d4477e3f3d06188b8837b571d7257c3e375507 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_69.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_69.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdfdae51ebeafb4cbf1eb8f8960b94cd4adab373 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_69.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abfe0d30721df35c48bfc843ddc66881017e4913f7e13eec6164cf25582a26c3 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_7.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..55ef6b38a0e83e04ee1f0b3df2d877b60843477d --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:357df7b609d6ffd7f22b998281f7856a711ee83505e5ed2835959554b0185df7 +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_70.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_70.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd51b6b36ff88b776e869ceba87fd82c3a73ef95 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_70.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138472d229d941a4981504874fcb169fb5d571f5fc4d8bc6ce1d2f0ee99c62f8 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_71.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_71.pth new file mode 100644 index 0000000000000000000000000000000000000000..f760a4da6594dc63160e97598bc8a07b84122946 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_71.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da22abd8e6be58a917b8f501c9f703e0945481a30bc0c264e6076561ef880fe7 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_72.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_72.pth new file mode 100644 index 0000000000000000000000000000000000000000..04f15152d7e059c1f46ddc8ec1beaa8a2c337120 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_72.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73c1ee832627e7bb1c685f4daa4bc27d48de658ddc2d71a23b55ccbf4b53260 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_73.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_73.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbb9c90e8808d9f22a20af4c9a51298cc1354d9c --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_73.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d626a2351b36a83e0e6b651bd67b789654b923add0b0d6b040f69ddf63d891ae +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_74.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_74.pth new file mode 100644 index 0000000000000000000000000000000000000000..a244b8e2c1d3fcb0ac56b28f8e3d5d0fb7990d6f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_74.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99dbd8acca5e351ba41dcf362f4cf0e4cde30cf76c1d8bb3893c3cc4b757fef0 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_75.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_75.pth new file mode 100644 index 0000000000000000000000000000000000000000..7431c4e102b82798b3ccb16fa48bc617c42d4ab4 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_75.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd050598b703078997d2ec829302ed7bb1217afc84c53ab70f09e4d34e321137 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_76.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_76.pth new file mode 100644 index 0000000000000000000000000000000000000000..a24d0bdd6c18b76630c6a13a38c237f783614236 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_76.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7ae218ad2c425b491fc827516016d9438df9a719cae1f54d0fc18262b78952 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_77.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_77.pth new file mode 100644 index 0000000000000000000000000000000000000000..53a4a3c18f69e21d574b7b24d3de55520cd2631a --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_77.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b5b151d14dacd943c2ee76419efcc63704adf67d23d6f6b37613060b3c0c65 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_78.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_78.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c17239cdad91447cacc16fb04e66fc3a9c03d4a --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_78.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb33f68d7169f1547f777e1eb845a35f1c72543d09f501b13376a3c9916ebc92 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_79.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_79.pth new file mode 100644 index 0000000000000000000000000000000000000000..30b30f22a62413a95c3430f1dee610e0b83ed3a5 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_79.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24bb33c918ebda7265b1f4765ac83bddf1720202b4c26483ce2c82c1c523c9a +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_8.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_8.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5df3b151481e713fceb5286b52570bff91c1bb6 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_8.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb33667d752a94ade6841f62b8b8fcc22256b4712bd568b141bc690d4a42e11 +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_80.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_80.pth new file mode 100644 index 0000000000000000000000000000000000000000..452e25a9446eb8274f6d3b790f47d11f7bd724d1 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_80.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95fa93d8cf1781e42b37439f67fbab6c0f53bf2e90b71ef07084cd01ac232a5a +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_81.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_81.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c9e6ee57c06fb32b0dec59e68c961b15d5ffa2f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_81.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab6faf09aab23376ef8c2724dca0883113fd961f479910f2356ce4e7bfd07b6c +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_82.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_82.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa8c5ad7126f56c99af034d136596f50c888d8a0 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_82.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531a741ec36125e0b0737639496710f983be365d23f6d8dd6f8563b0a2ed676e +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_83.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_83.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ac53d904458a2dba1bc9846de14e060c7bd61ec --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_83.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ac69f7479a518726a892438fd2c5bb6ac3a196869d28b4486d5732228767af +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_84.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_84.pth new file mode 100644 index 0000000000000000000000000000000000000000..efe5df0c9e8370db648a0a927044b0785b0e4419 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_84.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433f29dce26db8e24d4f3d4664e1447db730d01325b49bcc8cf4809c00244808 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_85.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_85.pth new file mode 100644 index 0000000000000000000000000000000000000000..2896848bf8bedb7369a7fdc57b50c0f34b2339c3 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_85.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efdbd9488405e24eb2e493ba4366a8efb033cb465c827ab4056d155b38719315 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_86.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_86.pth new file mode 100644 index 0000000000000000000000000000000000000000..0bf4b819eae182bed93659fd9cf59f12f423b399 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_86.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53df33a07f627c34081928d88d11d078b24f6b875effe49f81d59dcd56f857b3 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_87.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_87.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dd7957b3e52b915950d2893c360c42de09e1e1b --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_87.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012f822f0e96a6bd8e09d6c6bd2afc44e27493005ed52ee410fb07f62342df50 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_88.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_88.pth new file mode 100644 index 0000000000000000000000000000000000000000..1fd73fa7aecddfdab2e2462a6f0a7567b8eac529 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_88.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9d110550ec73c0ecc58512f9a01f6149980a36f61bf4fd02a4ff27b754ff98 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_89.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_89.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fb61c8e3e9ae9cbd8971a8a616c6a5210b97f3e --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_89.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46083c57e28388453140def62122184fe81394c41f4a37b8c73609dbccc6cd4c +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_9.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_9.pth new file mode 100644 index 0000000000000000000000000000000000000000..02f947ea3a1f7648ad22a0700485824c7b8dc625 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_9.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354a7a38e97ba11b8ad29bf4d00d74f92295b32124cff0ef46baa862aa9b0f2f +size 14469 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_90.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_90.pth new file mode 100644 index 0000000000000000000000000000000000000000..454d297796dc845be5ca23408d086ca84cb3321f --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_90.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ce591153a42d0a7bb04d17d9663c9b92c86a845d2f18e995bff7206d00cdfb +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_91.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_91.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdb6694356fa60781474d6305285da8bf001733c --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_91.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9962f9913c6ac7dabbb71d2357499fdde872456490855ce2bbb1dc277794beba +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_92.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_92.pth new file mode 100644 index 0000000000000000000000000000000000000000..cedd53b15ca7e86566023d613a043650403486db --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_92.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d6356013347c130ec159765a31629052c2a3f731a2c23535c8c194290c9624 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_93.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_93.pth new file mode 100644 index 0000000000000000000000000000000000000000..34dc0d515f025aa7f494638194bcb0094c465b72 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_93.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b727b42bb7003b910ef8d6eafe793052664d36134a53329df18a38f490edf8 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_94.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_94.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b9c8b0bb13114b9f62678f15685648b5085100c --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_94.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40fdb6c83be56af5ed2cc1a3e0878343f8da520ff58c290749b9b97aac35ba48 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_95.pth b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_95.pth new file mode 100644 index 0000000000000000000000000000000000000000..857b3a0203b0ef034929afb17e649dbbb6459a19 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_95.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23fe88b52ecc80825aa0f90748acf61037f01b97d68813f2179065ca1b9dc1b5 +size 14476 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/scheduler.pt b/g1_0_baseline_original_code__edit/pre-anneal/500M/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..250b92b2410c931750ba561cfa60596774ce941c --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4997a19d117878d71eb94352d555dcaa54875b0abe7b5c01497301d7134cc713 +size 1465 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..890ddaefca8201dd023c4f013db5ce492d12e7e0 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6 +size 32170070 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer_config.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ecf064451d225c9fc2487f9743cf14bbd133ba57 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer_config.json @@ -0,0 +1,56 @@ +{ + "audio_token": "<|audio|>", + "backend": "tokenizers", + "boa_token": "<|audio>", + "boi_token": "<|image>", + "bos_token": "", + "eoa_token": "", + "eoc_token": "", + "eoi_token": "", + "eos_token": "", + "eot_token": "", + "escape_token": "<|\"|>", + "etc_token": "", + "etd_token": "", + "etr_token": "", + "extra_special_tokens": [ + "<|video|>" + ], + "image_token": "<|image|>", + "is_local": true, + "local_files_only": true, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "model_specific_special_tokens": { + "audio_token": "<|audio|>", + "boa_token": "<|audio>", + "boi_token": "<|image>", + "eoa_token": "", + "eoc_token": "", + "eoi_token": "", + "eot_token": "", + "escape_token": "<|\"|>", + "etc_token": "", + "etd_token": "", + "etr_token": "", + "image_token": "<|image|>", + "soc_token": "<|channel>", + "sot_token": "<|turn>", + "stc_token": "<|tool_call>", + "std_token": "<|tool>", + "str_token": "<|tool_response>", + "think_token": "<|think|>" + }, + "pad_token": "", + "padding_side": "right", + "processor_class": "Gemma4Processor", + "soc_token": "<|channel>", + "sot_token": "<|turn>", + "split_special_tokens": false, + "stc_token": "<|tool_call>", + "std_token": "<|tool>", + "str_token": "<|tool_response>", + "think_token": "<|think|>", + "tokenizer_class": "GemmaTokenizer", + "unk_token": "" +} diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/trainer_state.json b/g1_0_baseline_original_code__edit/pre-anneal/500M/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6e7de402a3d2a4ff2a4419bb3345b9a1ff2a423e --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/trainer_state.json @@ -0,0 +1,475 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.33473684210526317, + "eval_steps": 500, + "global_step": 636, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.005263157894736842, + "grad_norm": 277.9251550700308, + "learning_rate": 8.240909090909092e-06, + "loss": 1.1935880661010743, + "step": 10 + }, + { + "epoch": 0.010526315789473684, + "grad_norm": 476.2440273553255, + "learning_rate": 1.728636363636364e-05, + "loss": 0.6812121391296386, + "step": 20 + }, + { + "epoch": 0.015789473684210527, + "grad_norm": 553.066381041332, + "learning_rate": 2e-05, + "loss": 0.6774760246276855, + "step": 30 + }, + { + "epoch": 0.021052631578947368, + "grad_norm": 238.39033250066225, + "learning_rate": 2e-05, + "loss": 0.717523717880249, + "step": 40 + }, + { + "epoch": 0.02631578947368421, + "grad_norm": 6.423600996484986, + "learning_rate": 2e-05, + "loss": 0.698247241973877, + "step": 50 + }, + { + "epoch": 0.031578947368421054, + "grad_norm": 12.182632065759611, + "learning_rate": 2e-05, + "loss": 0.6801887920924595, + "step": 60 + }, + { + "epoch": 0.03684210526315789, + "grad_norm": 3.898925740910897, + "learning_rate": 2e-05, + "loss": 0.6852305889129638, + "step": 70 + }, + { + "epoch": 0.042105263157894736, + "grad_norm": 39.38983888155174, + "learning_rate": 2e-05, + "loss": 0.654410457611084, + "step": 80 + }, + { + "epoch": 0.04736842105263158, + "grad_norm": 3436.9100068126218, + "learning_rate": 2e-05, + "loss": 0.6581138610839844, + "step": 90 + }, + { + "epoch": 0.05263157894736842, + "grad_norm": 17.058263928095723, + "learning_rate": 2e-05, + "loss": 0.6698699951171875, + "step": 100 + }, + { + "epoch": 0.05789473684210526, + "grad_norm": 15.395610996536666, + "learning_rate": 2e-05, + "loss": 0.6855615377426147, + "step": 110 + }, + { + "epoch": 0.06315789473684211, + "grad_norm": 36.138069069168644, + "learning_rate": 2e-05, + "loss": 0.6700192928314209, + "step": 120 + }, + { + "epoch": 0.06842105263157895, + "grad_norm": 40.71179258778245, + "learning_rate": 2e-05, + "loss": 0.6440637111663818, + "step": 130 + }, + { + "epoch": 0.07368421052631578, + "grad_norm": 26.346783787386695, + "learning_rate": 2e-05, + "loss": 0.6517030715942382, + "step": 140 + }, + { + "epoch": 0.07894736842105263, + "grad_norm": 27.55788944270315, + "learning_rate": 2e-05, + "loss": 0.6310464382171631, + "step": 150 + }, + { + "epoch": 0.08421052631578947, + "grad_norm": 37.2896385769616, + "learning_rate": 2e-05, + "loss": 0.6036643385887146, + "step": 160 + }, + { + "epoch": 0.08947368421052632, + "grad_norm": 28.30562808987054, + "learning_rate": 2e-05, + "loss": 0.6304524421691895, + "step": 170 + }, + { + "epoch": 0.09473684210526316, + "grad_norm": 8.226178615945107, + "learning_rate": 2e-05, + "loss": 0.6399477958679199, + "step": 180 + }, + { + "epoch": 0.1, + "grad_norm": 12.911539739208802, + "learning_rate": 2e-05, + "loss": 0.6609909057617187, + "step": 190 + }, + { + "epoch": 0.10526315789473684, + "grad_norm": 5.375688884949072, + "learning_rate": 2e-05, + "loss": 0.700928783416748, + "step": 200 + }, + { + "epoch": 0.11052631578947368, + "grad_norm": 2.7336799555608633, + "learning_rate": 2e-05, + "loss": 0.6656771659851074, + "step": 210 + }, + { + "epoch": 0.11578947368421053, + "grad_norm": 1.273028977260435, + "learning_rate": 2e-05, + "loss": 0.6465655565261841, + "step": 220 + }, + { + "epoch": 0.12105263157894737, + "grad_norm": 4.061486354346769, + "learning_rate": 2e-05, + "loss": 0.6510947227478028, + "step": 230 + }, + { + "epoch": 0.12631578947368421, + "grad_norm": 17.08564765461719, + "learning_rate": 2e-05, + "loss": 0.6056292533874512, + "step": 240 + }, + { + "epoch": 0.13157894736842105, + "grad_norm": 1.7229654353674664, + "learning_rate": 2e-05, + "loss": 0.6070424556732178, + "step": 250 + }, + { + "epoch": 0.1368421052631579, + "grad_norm": 9.390509748716465, + "learning_rate": 2e-05, + "loss": 0.6267301082611084, + "step": 260 + }, + { + "epoch": 0.14210526315789473, + "grad_norm": 15.400512770566671, + "learning_rate": 2e-05, + "loss": 0.6391798973083496, + "step": 270 + }, + { + "epoch": 0.14736842105263157, + "grad_norm": 61.4253929989291, + "learning_rate": 2e-05, + "loss": 0.6568265438079834, + "step": 280 + }, + { + "epoch": 0.15263157894736842, + "grad_norm": 22.257639018151185, + "learning_rate": 2e-05, + "loss": 0.6847233772277832, + "step": 290 + }, + { + "epoch": 0.15789473684210525, + "grad_norm": 7.638398547207429, + "learning_rate": 2e-05, + "loss": 0.6530518531799316, + "step": 300 + }, + { + "epoch": 0.1631578947368421, + "grad_norm": 1.4003289128042544, + "learning_rate": 2e-05, + "loss": 0.643625020980835, + "step": 310 + }, + { + "epoch": 0.16842105263157894, + "grad_norm": 4.119716880544318, + "learning_rate": 2e-05, + "loss": 0.610459566116333, + "step": 320 + }, + { + "epoch": 0.1736842105263158, + "grad_norm": 1.1046654687087005, + "learning_rate": 2e-05, + "loss": 0.6272223949432373, + "step": 330 + }, + { + "epoch": 0.17894736842105263, + "grad_norm": 1.7033347850189349, + "learning_rate": 2e-05, + "loss": 0.624421501159668, + "step": 340 + }, + { + "epoch": 0.18421052631578946, + "grad_norm": 1.2851543875888867, + "learning_rate": 2e-05, + "loss": 0.6151554107666015, + "step": 350 + }, + { + "epoch": 0.18947368421052632, + "grad_norm": 0.7005721761354591, + "learning_rate": 2e-05, + "loss": 0.6391288757324218, + "step": 360 + }, + { + "epoch": 0.19473684210526315, + "grad_norm": 0.6998229739862576, + "learning_rate": 2e-05, + "loss": 0.6103288173675537, + "step": 370 + }, + { + "epoch": 0.2, + "grad_norm": 0.7846658395091977, + "learning_rate": 2e-05, + "loss": 0.6030592388576932, + "step": 380 + }, + { + "epoch": 0.20526315789473684, + "grad_norm": 0.7754097519377567, + "learning_rate": 2e-05, + "loss": 0.6054659843444824, + "step": 390 + }, + { + "epoch": 0.21052631578947367, + "grad_norm": 1.2645928657614174, + "learning_rate": 2e-05, + "loss": 0.5886777877807617, + "step": 400 + }, + { + "epoch": 0.21578947368421053, + "grad_norm": 1.2392601205700426, + "learning_rate": 2e-05, + "loss": 0.6051255702972412, + "step": 410 + }, + { + "epoch": 0.22105263157894736, + "grad_norm": 2.0562235987600745, + "learning_rate": 2e-05, + "loss": 0.5852577209472656, + "step": 420 + }, + { + "epoch": 0.22631578947368422, + "grad_norm": 0.7384383099188049, + "learning_rate": 2e-05, + "loss": 0.5996756553649902, + "step": 430 + }, + { + "epoch": 0.23157894736842105, + "grad_norm": 7.949426487862018, + "learning_rate": 2e-05, + "loss": 0.5924458980560303, + "step": 440 + }, + { + "epoch": 0.23684210526315788, + "grad_norm": 2.406961337574789, + "learning_rate": 2e-05, + "loss": 0.5782783508300782, + "step": 450 + }, + { + "epoch": 0.24210526315789474, + "grad_norm": 2.4617743368215264, + "learning_rate": 2e-05, + "loss": 0.5781107902526855, + "step": 460 + }, + { + "epoch": 0.24736842105263157, + "grad_norm": 6.181209324709119, + "learning_rate": 2e-05, + "loss": 0.5929227352142334, + "step": 470 + }, + { + "epoch": 0.25263157894736843, + "grad_norm": 0.9845224125322452, + "learning_rate": 2e-05, + "loss": 0.5934472878774008, + "step": 480 + }, + { + "epoch": 0.2578947368421053, + "grad_norm": 0.7695348863013695, + "learning_rate": 2e-05, + "loss": 0.6078689575195313, + "step": 490 + }, + { + "epoch": 0.2631578947368421, + "grad_norm": 0.868029792269646, + "learning_rate": 2e-05, + "loss": 0.5850549221038819, + "step": 500 + }, + { + "epoch": 0.26842105263157895, + "grad_norm": 7.10665696890153, + "learning_rate": 2e-05, + "loss": 0.5906089782714844, + "step": 510 + }, + { + "epoch": 0.2736842105263158, + "grad_norm": 2.085002515371101, + "learning_rate": 2e-05, + "loss": 0.5627097129821778, + "step": 520 + }, + { + "epoch": 0.2789473684210526, + "grad_norm": 3.24996122814419, + "learning_rate": 2e-05, + "loss": 0.5842923641204834, + "step": 530 + }, + { + "epoch": 0.28421052631578947, + "grad_norm": 2.77743902539448, + "learning_rate": 2e-05, + "loss": 0.583029317855835, + "step": 540 + }, + { + "epoch": 0.2894736842105263, + "grad_norm": 1.00107362018166, + "learning_rate": 2e-05, + "loss": 0.5788339614868164, + "step": 550 + }, + { + "epoch": 0.29473684210526313, + "grad_norm": 6.715842466313377, + "learning_rate": 2e-05, + "loss": 0.577792739868164, + "step": 560 + }, + { + "epoch": 0.3, + "grad_norm": 4.914995797479727, + "learning_rate": 2e-05, + "loss": 0.5856772422790527, + "step": 570 + }, + { + "epoch": 0.30526315789473685, + "grad_norm": 7.929082186600778, + "learning_rate": 2e-05, + "loss": 0.5759101390838623, + "step": 580 + }, + { + "epoch": 0.3105263157894737, + "grad_norm": 4.248693287461714, + "learning_rate": 2e-05, + "loss": 0.5559419631958008, + "step": 590 + }, + { + "epoch": 0.3157894736842105, + "grad_norm": 2.29449479907879, + "learning_rate": 2e-05, + "loss": 0.5724806785583496, + "step": 600 + }, + { + "epoch": 0.32105263157894737, + "grad_norm": 0.8396044362099533, + "learning_rate": 2e-05, + "loss": 0.5718889236450195, + "step": 610 + }, + { + "epoch": 0.3263157894736842, + "grad_norm": 1.0964682326153241, + "learning_rate": 2e-05, + "loss": 0.5632170677185059, + "step": 620 + }, + { + "epoch": 0.33157894736842103, + "grad_norm": 1.4575940660913673, + "learning_rate": 2e-05, + "loss": 0.5833041191101074, + "step": 630 + } + ], + "logging_steps": 10, + "max_steps": 1272, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 53, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4380775541637120.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/training_args.bin b/g1_0_baseline_original_code__edit/pre-anneal/500M/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c8780750404183d44209d56a046940bed676e4c --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb89b8dc0f1655e2eab3cb9bb1897a814288ec347b907f6ad549a0c02a4eb6e8 +size 8273 diff --git a/g1_0_baseline_original_code__edit/pre-anneal/500M/zero_to_fp32.py b/g1_0_baseline_original_code__edit/pre-anneal/500M/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..5995d6e6f04e43b989587aa9022a3aef0c66d694 --- /dev/null +++ b/g1_0_baseline_original_code__edit/pre-anneal/500M/zero_to_fp32.py @@ -0,0 +1,760 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: +# python zero_to_fp32.py . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import gc +import json +import numpy as np +from tqdm import tqdm +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device, weights_only=False) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + total_files = len(files) + state_dicts = [] + for f in tqdm(files, desc='Loading checkpoint shards'): + state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +class GatheredTensor: + """ + A pseudo tensor that collects partitioned weights. + It is more memory efficient when there are multiple groups. + """ + + def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape): + self.flat_groups = flat_groups + self.flat_groups_offset = flat_groups_offset + self.offset = offset + self.partitioned_numel = partitioned_numel + self.shape = shape + self.dtype = self.flat_groups[0][0].dtype + + def contiguous(self): + """ + Merge partitioned weights from flat_groups into a single tensor. + """ + end_idx = self.offset + self.partitioned_numel + world_size = len(self.flat_groups) + pad_flat_param_chunks = [] + + for rank_i in range(world_size): + # for each rank, we need to collect weights from related group/groups + flat_groups_at_rank_i = self.flat_groups[rank_i] + start_group_id = None + end_group_id = None + for group_id in range(len(self.flat_groups_offset)): + if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]: + start_group_id = group_id + if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]: + end_group_id = group_id + break + # collect weights from related group/groups + for group_id in range(start_group_id, end_group_id + 1): + flat_tensor = flat_groups_at_rank_i[group_id] + start_offset = self.offset - self.flat_groups_offset[group_id] + end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id] + pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset]) + + # collect weights from all ranks + pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0) + param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous() + return param + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size + + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]])) + for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'): + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # memory efficient tensor + tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape) + state_dict[name] = tensor + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def to_torch_tensor(state_dict, return_empty_tensor=False): + """ + Convert state_dict of GatheredTensor to torch tensor + """ + torch_state_dict = {} + converted_tensors = {} + for name, tensor in state_dict.items(): + tensor_id = id(tensor) + if tensor_id in converted_tensors: # shared tensors + shared_tensor = torch_state_dict[converted_tensors[tensor_id]] + torch_state_dict[name] = shared_tensor + else: + converted_tensors[tensor_id] = name + if return_empty_tensor: + torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype) + else: + torch_state_dict[name] = tensor.contiguous() + return torch_state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag=None, + exclude_frozen_parameters=False, + lazy_mode=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient. + Convert the pesduo tensor to torch tensor by ``.contiguous()`` + + Returns: + - pytorch ``state_dict`` + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + Note: the above usage may not work if your application doesn't have sufficient free CPU memory. + You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. Or you can load state_dict in lazy mode :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu + for name, lazy_tensor in state_dict.item(): + tensor = lazy_tensor.contiguous() # to cpu + print(name, tensor) + # del tensor to release memory if it no longer in use + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + if lazy_mode: + return state_dict + else: + return to_torch_tensor(state_dict) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag, + exclude_frozen_parameters, + lazy_mode=True) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + # an memory-efficient approach for sharding + empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True) + state_dict_split = split_torch_state_dict_into_shards(empty_state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model by shard + os.makedirs(output_dir, exist_ok=True) + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors} + shard_state_dict = to_torch_tensor(shard_state_dict) + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard_state_dict, output_path, metadata={"format": "pt"}) + else: + torch.save(shard_state_dict, output_path) + # release the memory of current shard + for tensor_name in list(shard_state_dict.keys()): + del state_dict[tensor_name] + del shard_state_dict[tensor_name] + del shard_state_dict + gc.collect() + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info("Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info("Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument("output_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters)