Add files using upload-large-folder tool

.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 +1,133 @@
+{%- set default_system_prompt = "You are a strict, zero-tolerance parental control content-safety guardrail classifier for visual media.\nYour role is minor protection: any media containing suggestive, revealing, sexually provocative, or explicit visual elements must be flagged as NSFW.\n\nSTRICT ZERO-TOLERANCE CLASSIFICATION RULES:\n1. Nudity & Exposure: Any full or partial nudity, exposed breasts, cleavage, buttocks, groin, or visible pubic area MUST be classified as NSFW.\n2. Underwear & Swimwear: Thongs, G-strings, micro-bikinis, skimpy/revealing swimwear, bras, panties, lingerie, see-through clothing, or unbuttoned tops revealing undergarments/bare torsos MUST be classified as NSFW.\n3. Poses & Suggestiveness: Sexually suggestive poses, seductive modeling, cleavage-emphasizing framing, fetish content, or explicit erotic themes MUST be classified as NSFW.\n4. Artwork & Animation: Anime nudes, ecchi, hentai, suggestive illustrations, or 2D/3D stylized erotica MUST be classified as NSFW.\n5. Classification Threshold: When in doubt, err on the side of caution and classify the content as NSFW (nsfw = 1, safe = 0).\n\nOutput strictly valid JSON with no extra conversational text, commentary, or markdown formatting outside the JSON object:\n{\n  \"caption\": \"<Detailed, objective visual description of the subject, clothing, exposure, and pose>\",\n  \"is_nsfw\": true | false,\n  \"reason\": \"<Precise reason for classification based on clothing, exposure, or pose>\",\n  \"nsfw\": 1 | 0,\n  \"safe\": 1 | 0\n}" %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- else %}
+        {{- default_system_prompt + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\n' + default_system_prompt + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {%- if '</think>' in message.content %}
+                {{- message.content.split('</think>')[-1].lstrip('\n') }}
+            {%- else %}
+                {{- message.content }}
+            {%- endif %}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {%- if '</think>' in content_item.text %}
+                        {{- content_item.text.split('</think>')[-1].lstrip('\n') }}
+                    {%- else %}
+                        {{- content_item.text }}
+                    {%- endif %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.16.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cf1cb4edef6449106b77648a2f3e4612dd483fc4e66671e191ae6c19f2b345
+size 2082094072

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558f0d85439a88b6eb9569add4f7c46135557805a040e73250904c54632320a9
+size 2098036664

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86da326c57f2ba44b9de2416e460d729ab1ef715b427d494f9c8d6997c561b5
+size 75009360

model.safetensors.index.json

@@ -0,0 +1,633 @@
+{
+  "metadata": {
+    "total_parameters": 2127532032,
+    "total_size": 4255064064
+  },
+  "weight_map": {
+    "model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00003-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00003-of-00003.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00003-of-00003.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00003-of-00003.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00003-of-00003.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00003-of-00003.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00003-of-00003.safetensors",
+    "model.visual.merger.norm.bias": "model-00003-of-00003.safetensors",
+    "model.visual.merger.norm.weight": "model-00003-of-00003.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00003-of-00003.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00003-of-00003.safetensors",
+    "model.visual.pos_embed.weight": "model-00003-of-00003.safetensors"
+  }
+}

processor_config.json

@@ -0,0 +1,65 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_video_tokens": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec81cf4cd3712164ba5c12a479975a0d80142cf066a39632c941c5b40e569bff
+size 11422917

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": 2048,
+  "model_max_length": 262144,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}