Upload folder using huggingface_hub

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- else %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                <|vision_start|><|image_pad|><|vision_end|>\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                <|vision_start|><|video_pad|><|vision_end|>\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- render_content(messages[0].content, false) + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false) %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, True) %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,318 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "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": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 25600,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "ignored_layers": [
+      "lm_head",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.merger.norm",
+      "model.visual.patch_embed.proj",
+      "model.visual.pos_embed",
+      "visual.merger.linear_fc1",
+      "visual.merger.linear_fc2",
+      "visual.merger.norm",
+      "visual.patch_embed.proj",
+      "visual.pos_embed",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "visual.blocks.0.attn.proj",
+      "visual.blocks.0.attn.qkv_proj",
+      "visual.blocks.0.mlp.linear_fc1",
+      "visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "visual.blocks.1.attn.proj",
+      "visual.blocks.1.attn.qkv_proj",
+      "visual.blocks.1.mlp.linear_fc1",
+      "visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "visual.blocks.2.attn.proj",
+      "visual.blocks.2.attn.qkv_proj",
+      "visual.blocks.2.mlp.linear_fc1",
+      "visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "visual.blocks.3.attn.proj",
+      "visual.blocks.3.attn.qkv_proj",
+      "visual.blocks.3.mlp.linear_fc1",
+      "visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "visual.blocks.4.attn.proj",
+      "visual.blocks.4.attn.qkv_proj",
+      "visual.blocks.4.mlp.linear_fc1",
+      "visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "visual.blocks.5.attn.proj",
+      "visual.blocks.5.attn.qkv_proj",
+      "visual.blocks.5.mlp.linear_fc1",
+      "visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "visual.blocks.6.attn.proj",
+      "visual.blocks.6.attn.qkv_proj",
+      "visual.blocks.6.mlp.linear_fc1",
+      "visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "visual.blocks.7.attn.proj",
+      "visual.blocks.7.attn.qkv_proj",
+      "visual.blocks.7.mlp.linear_fc1",
+      "visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "visual.blocks.8.attn.proj",
+      "visual.blocks.8.attn.qkv_proj",
+      "visual.blocks.8.mlp.linear_fc1",
+      "visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "visual.blocks.9.attn.proj",
+      "visual.blocks.9.attn.qkv_proj",
+      "visual.blocks.9.mlp.linear_fc1",
+      "visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "visual.blocks.10.attn.proj",
+      "visual.blocks.10.attn.qkv_proj",
+      "visual.blocks.10.mlp.linear_fc1",
+      "visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "visual.blocks.11.attn.proj",
+      "visual.blocks.11.attn.qkv_proj",
+      "visual.blocks.11.mlp.linear_fc1",
+      "visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "visual.blocks.12.attn.proj",
+      "visual.blocks.12.attn.qkv_proj",
+      "visual.blocks.12.mlp.linear_fc1",
+      "visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "visual.blocks.13.attn.proj",
+      "visual.blocks.13.attn.qkv_proj",
+      "visual.blocks.13.mlp.linear_fc1",
+      "visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "visual.blocks.14.attn.proj",
+      "visual.blocks.14.attn.qkv_proj",
+      "visual.blocks.14.mlp.linear_fc1",
+      "visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "visual.blocks.15.attn.proj",
+      "visual.blocks.15.attn.qkv_proj",
+      "visual.blocks.15.mlp.linear_fc1",
+      "visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "visual.blocks.16.attn.proj",
+      "visual.blocks.16.attn.qkv_proj",
+      "visual.blocks.16.mlp.linear_fc1",
+      "visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "visual.blocks.17.attn.proj",
+      "visual.blocks.17.attn.qkv_proj",
+      "visual.blocks.17.mlp.linear_fc1",
+      "visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "visual.blocks.18.attn.proj",
+      "visual.blocks.18.attn.qkv_proj",
+      "visual.blocks.18.mlp.linear_fc1",
+      "visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "visual.blocks.19.attn.proj",
+      "visual.blocks.19.attn.qkv_proj",
+      "visual.blocks.19.mlp.linear_fc1",
+      "visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "visual.blocks.20.attn.proj",
+      "visual.blocks.20.attn.qkv_proj",
+      "visual.blocks.20.mlp.linear_fc1",
+      "visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "visual.blocks.21.attn.proj",
+      "visual.blocks.21.attn.qkv_proj",
+      "visual.blocks.21.mlp.linear_fc1",
+      "visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "visual.blocks.22.attn.proj",
+      "visual.blocks.22.attn.qkv_proj",
+      "visual.blocks.22.mlp.linear_fc1",
+      "visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "visual.blocks.23.attn.proj",
+      "visual.blocks.23.attn.qkv_proj",
+      "visual.blocks.23.mlp.linear_fc1",
+      "visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "visual.blocks.24.attn.proj",
+      "visual.blocks.24.attn.qkv_proj",
+      "visual.blocks.24.mlp.linear_fc1",
+      "visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "visual.blocks.25.attn.proj",
+      "visual.blocks.25.attn.qkv_proj",
+      "visual.blocks.25.mlp.linear_fc1",
+      "visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "visual.blocks.26.attn.proj",
+      "visual.blocks.26.attn.qkv_proj",
+      "visual.blocks.26.mlp.linear_fc1",
+      "visual.blocks.26.mlp.linear_fc2",
+      "model.visual.deepstack_merger_list.0.linear_fc1",
+      "model.visual.deepstack_merger_list.0.linear_fc2",
+      "model.visual.deepstack_merger_list.0.norm",
+      "visual.deepstack_merger_list.0.linear_fc1",
+      "visual.deepstack_merger_list.0.linear_fc2",
+      "visual.deepstack_merger_list.0.norm",
+      "model.visual.deepstack_merger_list.1.linear_fc1",
+      "model.visual.deepstack_merger_list.1.linear_fc2",
+      "model.visual.deepstack_merger_list.1.norm",
+      "visual.deepstack_merger_list.1.linear_fc1",
+      "visual.deepstack_merger_list.1.linear_fc2",
+      "visual.deepstack_merger_list.1.norm",
+      "model.visual.deepstack_merger_list.2.linear_fc1",
+      "model.visual.deepstack_merger_list.2.linear_fc2",
+      "model.visual.deepstack_merger_list.2.norm",
+      "visual.deepstack_merger_list.2.linear_fc1",
+      "visual.deepstack_merger_list.2.linear_fc2",
+      "visual.deepstack_merger_list.2.norm"
+    ],
+    "weight_block_size": [
+      128,
+      128
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "top_k": 20,
+  "top_p": 0.95,
+  "repetition_penalty": 1.0,
+  "temperature": 0.8,
+  "transformers_version": "4.56.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec789744e6eb67552e4f823677233740d1d8c066f1a020623a842191ae42f0e6
+size 5324789312

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68bc10a72221f49da85a15e31a4786c14c60dfc773436db7a284a1002c98ef3
+size 5365032312

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ebbb248f80779909d81641cf107106240d7e1ef0616710e7f8b8e9dc1aaa12
+size 5365032312

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813a2a4c8b785e6c5037c668acd0b9f36cc250b243132d2ecee47c2cd30e9285
+size 5365032312

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ddf87034ce9a81f4ab81af45ac1d74005c09d3819c1a88bc02f49960b70eb77
+size 5365032312

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426b4ce0630a3bb91169a6ef9cfd13bdf28f2245c18a315d29d11c6f9eb21351
+size 5365032312

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403b509e3cb720ec7064bfd2a4a5ccd1c3ec4e1c8bd8f956587d02d97e2f31f2
+size 3367015312

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Qwen3VLProcessor",
+  "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- else %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                <|vision_start|><|image_pad|><|vision_end|>\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                <|vision_start|><|video_pad|><|vision_end|>\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- render_content(messages[0].content, false) + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false) %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, True) %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}