Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +110 -0
- config.json +217 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +39 -0
- recipe.yaml +6 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if do_vision_count %}
|
| 10 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 13 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 14 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 15 |
+
{%- if do_vision_count %}
|
| 16 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 19 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 20 |
+
{%- elif 'text' in item %}
|
| 21 |
+
{{- item.text }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- endfor %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- endmacro %}
|
| 26 |
+
{%- if tools %}
|
| 27 |
+
{{- '<|im_start|>system\n' }}
|
| 28 |
+
{%- if messages[0].role == 'system' %}
|
| 29 |
+
{{- render_content(messages[0].content, false) + '\n\n' }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{{- "# 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>" }}
|
| 32 |
+
{%- for tool in tools %}
|
| 33 |
+
{{- "\n" }}
|
| 34 |
+
{{- tool | tojson }}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{{- "\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" }}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if messages[0].role == 'system' %}
|
| 39 |
+
{{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 43 |
+
{%- for message in messages[::-1] %}
|
| 44 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 45 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 46 |
+
{%- set content = render_content(message.content, false) %}
|
| 47 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 48 |
+
{%- set ns.multi_step_tool = false %}
|
| 49 |
+
{%- set ns.last_query_index = index %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- endfor %}
|
| 53 |
+
{%- for message in messages %}
|
| 54 |
+
{%- set content = render_content(message.content, True) %}
|
| 55 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 56 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 57 |
+
{%- elif message.role == "assistant" %}
|
| 58 |
+
{%- set reasoning_content = '' %}
|
| 59 |
+
{%- if message.reasoning_content is string %}
|
| 60 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if '</think>' in content %}
|
| 63 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 64 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 68 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 69 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- else %}
|
| 74 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- if message.tool_calls %}
|
| 77 |
+
{%- for tool_call in message.tool_calls %}
|
| 78 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 79 |
+
{{- '\n' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- if tool_call.function %}
|
| 82 |
+
{%- set tool_call = tool_call.function %}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 85 |
+
{{- tool_call.name }}
|
| 86 |
+
{{- '", "arguments": ' }}
|
| 87 |
+
{%- if tool_call.arguments is string %}
|
| 88 |
+
{{- tool_call.arguments }}
|
| 89 |
+
{%- else %}
|
| 90 |
+
{{- tool_call.arguments | tojson }}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{{- '}\n</tool_call>' }}
|
| 93 |
+
{%- endfor %}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{{- '<|im_end|>\n' }}
|
| 96 |
+
{%- elif message.role == "tool" %}
|
| 97 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 98 |
+
{{- '<|im_start|>user' }}
|
| 99 |
+
{%- endif %}
|
| 100 |
+
{{- '\n<tool_response>\n' }}
|
| 101 |
+
{{- content }}
|
| 102 |
+
{{- '\n</tool_response>' }}
|
| 103 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 104 |
+
{{- '<|im_end|>\n' }}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- endif %}
|
| 107 |
+
{%- endfor %}
|
| 108 |
+
{%- if add_generation_prompt %}
|
| 109 |
+
{{- '<|im_start|>assistant\n' }}
|
| 110 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"image_token_id": 151655,
|
| 8 |
+
"model_type": "qwen3_vl",
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"quantization_config": {
|
| 11 |
+
"config_groups": {
|
| 12 |
+
"group_0": {
|
| 13 |
+
"format": "nvfp4-pack-quantized",
|
| 14 |
+
"input_activations": null,
|
| 15 |
+
"output_activations": null,
|
| 16 |
+
"targets": [
|
| 17 |
+
"Linear"
|
| 18 |
+
],
|
| 19 |
+
"weights": {
|
| 20 |
+
"actorder": null,
|
| 21 |
+
"block_structure": null,
|
| 22 |
+
"dynamic": false,
|
| 23 |
+
"group_size": 16,
|
| 24 |
+
"num_bits": 4,
|
| 25 |
+
"observer": "minmax",
|
| 26 |
+
"observer_kwargs": {},
|
| 27 |
+
"strategy": "tensor_group",
|
| 28 |
+
"symmetric": true,
|
| 29 |
+
"type": "float"
|
| 30 |
+
}
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"format": "nvfp4-pack-quantized",
|
| 34 |
+
"global_compression_ratio": null,
|
| 35 |
+
"ignore": [
|
| 36 |
+
"model.visual.blocks.0.attn.qkv",
|
| 37 |
+
"model.visual.blocks.0.attn.proj",
|
| 38 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 39 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 40 |
+
"model.visual.blocks.1.attn.qkv",
|
| 41 |
+
"model.visual.blocks.1.attn.proj",
|
| 42 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 43 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 44 |
+
"model.visual.blocks.2.attn.qkv",
|
| 45 |
+
"model.visual.blocks.2.attn.proj",
|
| 46 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 47 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 48 |
+
"model.visual.blocks.3.attn.qkv",
|
| 49 |
+
"model.visual.blocks.3.attn.proj",
|
| 50 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 51 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 52 |
+
"model.visual.blocks.4.attn.qkv",
|
| 53 |
+
"model.visual.blocks.4.attn.proj",
|
| 54 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 55 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 56 |
+
"model.visual.blocks.5.attn.qkv",
|
| 57 |
+
"model.visual.blocks.5.attn.proj",
|
| 58 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 59 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 60 |
+
"model.visual.blocks.6.attn.qkv",
|
| 61 |
+
"model.visual.blocks.6.attn.proj",
|
| 62 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 63 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 64 |
+
"model.visual.blocks.7.attn.qkv",
|
| 65 |
+
"model.visual.blocks.7.attn.proj",
|
| 66 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 67 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 68 |
+
"model.visual.blocks.8.attn.qkv",
|
| 69 |
+
"model.visual.blocks.8.attn.proj",
|
| 70 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 71 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 72 |
+
"model.visual.blocks.9.attn.qkv",
|
| 73 |
+
"model.visual.blocks.9.attn.proj",
|
| 74 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 75 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 76 |
+
"model.visual.blocks.10.attn.qkv",
|
| 77 |
+
"model.visual.blocks.10.attn.proj",
|
| 78 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 79 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 80 |
+
"model.visual.blocks.11.attn.qkv",
|
| 81 |
+
"model.visual.blocks.11.attn.proj",
|
| 82 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 83 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 84 |
+
"model.visual.blocks.12.attn.qkv",
|
| 85 |
+
"model.visual.blocks.12.attn.proj",
|
| 86 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 87 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 88 |
+
"model.visual.blocks.13.attn.qkv",
|
| 89 |
+
"model.visual.blocks.13.attn.proj",
|
| 90 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 91 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 92 |
+
"model.visual.blocks.14.attn.qkv",
|
| 93 |
+
"model.visual.blocks.14.attn.proj",
|
| 94 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 95 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 96 |
+
"model.visual.blocks.15.attn.qkv",
|
| 97 |
+
"model.visual.blocks.15.attn.proj",
|
| 98 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 99 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 100 |
+
"model.visual.blocks.16.attn.qkv",
|
| 101 |
+
"model.visual.blocks.16.attn.proj",
|
| 102 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 103 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 104 |
+
"model.visual.blocks.17.attn.qkv",
|
| 105 |
+
"model.visual.blocks.17.attn.proj",
|
| 106 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 107 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 108 |
+
"model.visual.blocks.18.attn.qkv",
|
| 109 |
+
"model.visual.blocks.18.attn.proj",
|
| 110 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 111 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 112 |
+
"model.visual.blocks.19.attn.qkv",
|
| 113 |
+
"model.visual.blocks.19.attn.proj",
|
| 114 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 115 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 116 |
+
"model.visual.blocks.20.attn.qkv",
|
| 117 |
+
"model.visual.blocks.20.attn.proj",
|
| 118 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 119 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 120 |
+
"model.visual.blocks.21.attn.qkv",
|
| 121 |
+
"model.visual.blocks.21.attn.proj",
|
| 122 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 123 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 124 |
+
"model.visual.blocks.22.attn.qkv",
|
| 125 |
+
"model.visual.blocks.22.attn.proj",
|
| 126 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 127 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 128 |
+
"model.visual.blocks.23.attn.qkv",
|
| 129 |
+
"model.visual.blocks.23.attn.proj",
|
| 130 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 131 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 132 |
+
"model.visual.blocks.24.attn.qkv",
|
| 133 |
+
"model.visual.blocks.24.attn.proj",
|
| 134 |
+
"model.visual.blocks.24.mlp.linear_fc1",
|
| 135 |
+
"model.visual.blocks.24.mlp.linear_fc2",
|
| 136 |
+
"model.visual.blocks.25.attn.qkv",
|
| 137 |
+
"model.visual.blocks.25.attn.proj",
|
| 138 |
+
"model.visual.blocks.25.mlp.linear_fc1",
|
| 139 |
+
"model.visual.blocks.25.mlp.linear_fc2",
|
| 140 |
+
"model.visual.blocks.26.attn.qkv",
|
| 141 |
+
"model.visual.blocks.26.attn.proj",
|
| 142 |
+
"model.visual.blocks.26.mlp.linear_fc1",
|
| 143 |
+
"model.visual.blocks.26.mlp.linear_fc2",
|
| 144 |
+
"model.visual.merger.linear_fc1",
|
| 145 |
+
"model.visual.merger.linear_fc2",
|
| 146 |
+
"model.visual.deepstack_merger_list.0.linear_fc1",
|
| 147 |
+
"model.visual.deepstack_merger_list.0.linear_fc2",
|
| 148 |
+
"model.visual.deepstack_merger_list.1.linear_fc1",
|
| 149 |
+
"model.visual.deepstack_merger_list.1.linear_fc2",
|
| 150 |
+
"model.visual.deepstack_merger_list.2.linear_fc1",
|
| 151 |
+
"model.visual.deepstack_merger_list.2.linear_fc2",
|
| 152 |
+
"lm_head"
|
| 153 |
+
],
|
| 154 |
+
"kv_cache_scheme": null,
|
| 155 |
+
"quant_method": "compressed-tensors",
|
| 156 |
+
"quantization_status": "compressed",
|
| 157 |
+
"sparsity_config": {},
|
| 158 |
+
"transform_config": {},
|
| 159 |
+
"version": "0.12.3.a20251030"
|
| 160 |
+
},
|
| 161 |
+
"text_config": {
|
| 162 |
+
"attention_bias": false,
|
| 163 |
+
"attention_dropout": 0.0,
|
| 164 |
+
"bos_token_id": 151643,
|
| 165 |
+
"dtype": "float32",
|
| 166 |
+
"eos_token_id": 151645,
|
| 167 |
+
"head_dim": 128,
|
| 168 |
+
"hidden_act": "silu",
|
| 169 |
+
"hidden_size": 4096,
|
| 170 |
+
"initializer_range": 0.02,
|
| 171 |
+
"intermediate_size": 12288,
|
| 172 |
+
"max_position_embeddings": 262144,
|
| 173 |
+
"model_type": "qwen3_vl_text",
|
| 174 |
+
"num_attention_heads": 32,
|
| 175 |
+
"num_hidden_layers": 36,
|
| 176 |
+
"num_key_value_heads": 8,
|
| 177 |
+
"rms_norm_eps": 1e-06,
|
| 178 |
+
"rope_scaling": {
|
| 179 |
+
"mrope_interleaved": true,
|
| 180 |
+
"mrope_section": [
|
| 181 |
+
24,
|
| 182 |
+
20,
|
| 183 |
+
20
|
| 184 |
+
],
|
| 185 |
+
"rope_type": "default"
|
| 186 |
+
},
|
| 187 |
+
"rope_theta": 5000000,
|
| 188 |
+
"use_cache": true,
|
| 189 |
+
"vocab_size": 151936
|
| 190 |
+
},
|
| 191 |
+
"tie_word_embeddings": false,
|
| 192 |
+
"transformers_version": "4.57.1",
|
| 193 |
+
"video_token_id": 151656,
|
| 194 |
+
"vision_config": {
|
| 195 |
+
"deepstack_visual_indexes": [
|
| 196 |
+
8,
|
| 197 |
+
16,
|
| 198 |
+
24
|
| 199 |
+
],
|
| 200 |
+
"depth": 27,
|
| 201 |
+
"dtype": "float32",
|
| 202 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 203 |
+
"hidden_size": 1152,
|
| 204 |
+
"in_channels": 3,
|
| 205 |
+
"initializer_range": 0.02,
|
| 206 |
+
"intermediate_size": 4304,
|
| 207 |
+
"model_type": "qwen3_vl",
|
| 208 |
+
"num_heads": 16,
|
| 209 |
+
"num_position_embeddings": 2304,
|
| 210 |
+
"out_hidden_size": 4096,
|
| 211 |
+
"patch_size": 16,
|
| 212 |
+
"spatial_merge_size": 2,
|
| 213 |
+
"temporal_patch_size": 2
|
| 214 |
+
},
|
| 215 |
+
"vision_end_token_id": 151653,
|
| 216 |
+
"vision_start_token_id": 151652
|
| 217 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"presence_penalty": 1.5,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac3a9150a6e4705ee85651a07ea52c1b08d1764b74eb5ed7968f849818d658e9
|
| 3 |
+
size 4983697236
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6820330d40122aa9fdcbe13e4024e6246c11eb0779bdd4b8a198cd80a7affa1c
|
| 3 |
+
size 3719561988
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e77430088b0107a241787d8311630d4d2608b7e05ab81ca585d52ef9e32afba
|
| 3 |
+
size 2489319552
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
recipe.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: [lm_head, 're:.*lm_head', 're:visual.*', 're:model.visual.*']
|
| 6 |
+
scheme: NVFP4A16
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"processor_class": "Qwen3VLProcessor",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|