Upload TEMPURA-InternVL3-8B weights

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
+' }}{% elif content['type'] == 'video' %}{{ '<video>
+' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
+'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,116 @@
+{
+  "architectures": [
+    "InternVLForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "downsample_ratio": 0.5,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_size": 3584,
+  "image_seq_length": 256,
+  "image_token_id": 151667,
+  "model_type": "internvl",
+  "pad_token_id": 151643,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "factor": 2.0,
+      "rope_theta": 1000000.0,
+      "rope_type": "dynamic",
+      "type": "dynamic"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151674
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "vision_config": {
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "image_size": [
+      448,
+      448
+    ],
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-06,
+    "layer_scale_init_value": 0.1,
+    "model_type": "internvl_vision",
+    "norm_type": "layer_norm",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": [
+      14,
+      14
+    ],
+    "projection_dropout": 0.0,
+    "use_absolute_position_embeddings": true,
+    "use_mask_token": false,
+    "use_mean_pooling": true,
+    "use_qk_norm": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "default"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "do_sample": false,
+  "eos_token_id": [
+    151645,
+    151645
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "5.3.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f39adb42843d37aa8f59522bdd1da7bd39fa7a3c4538ffed3743b8155dee7c2
+size 4971108816

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f8fc087b1e5b990ddfbb450dac18a49b79ba2434e54e31c2e653c3ad2494c7
+size 4932752816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fda84e46a39273c7d0e79e48382d6c9e4b4316eed1b80820be75ee4ec26747
+size 4991497848

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d62b4129c54b77c3cb9e41f38e8197f39e3ef19bcdbb58592c79e5ec5c01c58
+size 993486112

model.safetensors.index.json

@@ -0,0 +1,789 @@
+{
+  "metadata": {
+    "total_parameters": 7944373760,
+    "total_size": 15888747520
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.layer_norm.bias": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.embeddings.cls_token": "model-00004-of-00004.safetensors",
+    "vision_tower.embeddings.patch_embeddings.projection.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.embeddings.patch_embeddings.projection.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.embeddings.position_embeddings": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.projection_layer.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.projection_layer.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.attention.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.lambda_1": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.lambda_2": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.layernorm_after.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.layernorm_after.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.layernorm_before.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.layernorm_before.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_tower.encoder.layer.9.mlp.fc2.weight": "model-00004-of-00004.safetensors"
+  }
+}

processor_config.json

@@ -0,0 +1,64 @@
+{
+  "image_processor": {
+    "crop_to_patches": false,
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "image_processor_type": "GotOcr2ImageProcessorFast",
+    "image_std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "max_patches": 12,
+    "min_patches": 1,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 448,
+      "width": 448
+    }
+  },
+  "image_seq_length": 256,
+  "processor_class": "InternVLProcessor",
+  "video_processor": {
+    "crop_to_patches": false,
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "image_processor_type": "GotOcr2ImageProcessorFast",
+    "image_std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "initial_shift": true,
+    "max_patches": 12,
+    "min_patches": 1,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "height": 448,
+      "width": 448
+    },
+    "video_processor_type": "InternVLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0c8be238c81a5f0450067d9565e16794aef2699df631fcf3dd0c2ac4842b06
+size 11423728

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "context_image_token": "<IMG_CONTEXT>",
+  "crop_to_patches": false,
+  "end_image_token": "</img>",
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_end|>"
+  ],
+  "is_local": true,
+  "model_max_length": 32768,
+  "model_specific_special_tokens": {
+    "context_image_token": "<IMG_CONTEXT>",
+    "end_image_token": "</img>",
+    "start_image_token": "<img>",
+    "video_token": "<video>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "InternVLProcessor",
+  "return_token_type_ids": false,
+  "split_special_tokens": false,
+  "start_image_token": "<img>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<video>"
+}