Upload folder using huggingface_hub

.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

Modelfile

@@ -0,0 +1,16 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+SYSTEM """你是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。"""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

added_tokens.json

@@ -0,0 +1,34 @@
+{
+  "</box>": 151674,
+  "</img>": 151666,
+  "</quad>": 151670,
+  "</ref>": 151672,
+  "</tool_call>": 151658,
+  "<IMG_CONTEXT>": 151667,
+  "<box>": 151673,
+  "<img>": 151665,
+  "<quad>": 151669,
+  "<ref>": 151671,
+  "<tool_call>": 151657,
+  "<video>": 151668,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

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 +1,111 @@
+{
+  "architectures": [
+    "InternVLForConditionalGeneration"
+  ],
+  "downsample_ratio": 0.5,
+  "hidden_size": 3584,
+  "image_seq_length": 256,
+  "image_token_id": 151667,
+  "model_type": "internvl",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "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,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "factor": 2.0,
+      "rope_type": "dynamic",
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151674
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "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,
+    "torch_dtype": "bfloat16",
+    "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 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.53.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5087588774723573784e8e21533cd658fa96cc239a30a2d0399c3f246aa19d
+size 4877374576

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10823ce44fd0747de94c3a11b365d3347e854a3631a0b4673b9374fe4a5eade3
+size 4991497800

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9172daf9dd6664a6fc275d57c3b838a53e330744418cb9200910d25fbfa98099
+size 4932774744

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47665b99cd28b3e9fd2ba497c7a1230eb20d5cc348419c1f337ac228a76f1b4
+size 1087199376

model.safetensors.index.json

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

preprocessor_config.json

@@ -0,0 +1,34 @@
+{
+  "crop_size": null,
+  "crop_to_patches": false,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_patches": 12,
+  "min_patches": 1,
+  "processor_class": "InternVLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "InternVLProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
+  ],
+  "context_image_token": "<IMG_CONTEXT>",
+  "end_image_token": "</img>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "start_image_token": "<img>",
+  "video_token": "<video>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee033fc70630b62a96ed4701ca149577dd291131e454d86344b9cf91acf7979
+size 11423732

tokenizer_config.json

@@ -0,0 +1,308 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "context_image_token": "<IMG_CONTEXT>",
+  "end_image_token": "</img>",
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "context_image_token": "<IMG_CONTEXT>",
+    "end_image_token": "</img>",
+    "start_image_token": "<img>",
+    "video_token": "<video>"
+  },
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "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>"
+}

video_preprocessor_config.json

@@ -0,0 +1,90 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "do_sample_frames",
+    "video_metadata",
+    "fps",
+    "num_frames",
+    "initial_shift"
+  ],
+  "crop_size": null,
+  "crop_to_patches": false,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "GotOcr2ImageProcessorFast",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "initial_shift": true,
+  "input_data_format": null,
+  "max_patches": 12,
+  "min_patches": 1,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "do_sample_frames",
+    "video_metadata",
+    "fps",
+    "num_frames",
+    "initial_shift"
+  ],
+  "num_frames": null,
+  "processor_class": "InternVLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 448,
+    "width": 448
+  },
+  "size_divisor": null,
+  "video_metadata": null,
+  "video_processor_type": "InternVLVideoProcessor"
+}