Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +120 -0
- config.json +234 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00048.safetensors +3 -0
- model-00002-of-00048.safetensors +3 -0
- model-00004-of-00048.safetensors +3 -0
- model-00006-of-00048.safetensors +3 -0
- model-00007-of-00048.safetensors +3 -0
- model-00008-of-00048.safetensors +3 -0
- model-00009-of-00048.safetensors +3 -0
- model-00010-of-00048.safetensors +3 -0
- model-00011-of-00048.safetensors +3 -0
- model-00012-of-00048.safetensors +3 -0
- model-00013-of-00048.safetensors +3 -0
- model-00015-of-00048.safetensors +3 -0
- model-00021-of-00048.safetensors +3 -0
- model-00022-of-00048.safetensors +3 -0
- model-00023-of-00048.safetensors +3 -0
- model-00024-of-00048.safetensors +3 -0
- model-00025-of-00048.safetensors +3 -0
- model-00026-of-00048.safetensors +3 -0
- model-00027-of-00048.safetensors +3 -0
- model-00028-of-00048.safetensors +3 -0
- model-00029-of-00048.safetensors +3 -0
- model-00030-of-00048.safetensors +3 -0
- model-00031-of-00048.safetensors +3 -0
- model-00033-of-00048.safetensors +3 -0
- model-00034-of-00048.safetensors +3 -0
- model-00035-of-00048.safetensors +3 -0
- model-00036-of-00048.safetensors +3 -0
- model-00037-of-00048.safetensors +3 -0
- model-00038-of-00048.safetensors +3 -0
- model-00041-of-00048.safetensors +3 -0
- model-00042-of-00048.safetensors +3 -0
- model-00043-of-00048.safetensors +3 -0
- model-00044-of-00048.safetensors +3 -0
- model-00045-of-00048.safetensors +3 -0
- model-00046-of-00048.safetensors +3 -0
- model-00047-of-00048.safetensors +3 -0
- model-00048-of-00048.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +39 -0
- recipe.yaml +7 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- video_preprocessor_config.json +41 -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 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# 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>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\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" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLMoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl_moe",
|
| 8 |
+
"quantization_config": {
|
| 9 |
+
"config_groups": {
|
| 10 |
+
"group_0": {
|
| 11 |
+
"format": "float-quantized",
|
| 12 |
+
"input_activations": {
|
| 13 |
+
"actorder": null,
|
| 14 |
+
"block_structure": null,
|
| 15 |
+
"dynamic": true,
|
| 16 |
+
"group_size": 128,
|
| 17 |
+
"num_bits": 8,
|
| 18 |
+
"observer": null,
|
| 19 |
+
"observer_kwargs": {},
|
| 20 |
+
"strategy": "group",
|
| 21 |
+
"symmetric": true,
|
| 22 |
+
"type": "float"
|
| 23 |
+
},
|
| 24 |
+
"output_activations": null,
|
| 25 |
+
"targets": [
|
| 26 |
+
"Linear"
|
| 27 |
+
],
|
| 28 |
+
"weights": {
|
| 29 |
+
"actorder": null,
|
| 30 |
+
"block_structure": [
|
| 31 |
+
128,
|
| 32 |
+
128
|
| 33 |
+
],
|
| 34 |
+
"dynamic": false,
|
| 35 |
+
"group_size": null,
|
| 36 |
+
"num_bits": 8,
|
| 37 |
+
"observer": "minmax",
|
| 38 |
+
"observer_kwargs": {},
|
| 39 |
+
"strategy": "block",
|
| 40 |
+
"symmetric": true,
|
| 41 |
+
"type": "float"
|
| 42 |
+
}
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"format": "float-quantized",
|
| 46 |
+
"global_compression_ratio": null,
|
| 47 |
+
"ignore": [
|
| 48 |
+
"model.visual.blocks.0.attn.qkv",
|
| 49 |
+
"model.visual.blocks.0.attn.proj",
|
| 50 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 51 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 52 |
+
"model.visual.blocks.1.attn.qkv",
|
| 53 |
+
"model.visual.blocks.1.attn.proj",
|
| 54 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 55 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 56 |
+
"model.visual.blocks.2.attn.qkv",
|
| 57 |
+
"model.visual.blocks.2.attn.proj",
|
| 58 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 59 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 60 |
+
"model.visual.blocks.3.attn.qkv",
|
| 61 |
+
"model.visual.blocks.3.attn.proj",
|
| 62 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 63 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 64 |
+
"model.visual.blocks.4.attn.qkv",
|
| 65 |
+
"model.visual.blocks.4.attn.proj",
|
| 66 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 67 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 68 |
+
"model.visual.blocks.5.attn.qkv",
|
| 69 |
+
"model.visual.blocks.5.attn.proj",
|
| 70 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 71 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 72 |
+
"model.visual.blocks.6.attn.qkv",
|
| 73 |
+
"model.visual.blocks.6.attn.proj",
|
| 74 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 75 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 76 |
+
"model.visual.blocks.7.attn.qkv",
|
| 77 |
+
"model.visual.blocks.7.attn.proj",
|
| 78 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 79 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 80 |
+
"model.visual.blocks.8.attn.qkv",
|
| 81 |
+
"model.visual.blocks.8.attn.proj",
|
| 82 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 83 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 84 |
+
"model.visual.blocks.9.attn.qkv",
|
| 85 |
+
"model.visual.blocks.9.attn.proj",
|
| 86 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 87 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 88 |
+
"model.visual.blocks.10.attn.qkv",
|
| 89 |
+
"model.visual.blocks.10.attn.proj",
|
| 90 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 91 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 92 |
+
"model.visual.blocks.11.attn.qkv",
|
| 93 |
+
"model.visual.blocks.11.attn.proj",
|
| 94 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 95 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 96 |
+
"model.visual.blocks.12.attn.qkv",
|
| 97 |
+
"model.visual.blocks.12.attn.proj",
|
| 98 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 99 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 100 |
+
"model.visual.blocks.13.attn.qkv",
|
| 101 |
+
"model.visual.blocks.13.attn.proj",
|
| 102 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 103 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 104 |
+
"model.visual.blocks.14.attn.qkv",
|
| 105 |
+
"model.visual.blocks.14.attn.proj",
|
| 106 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 107 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 108 |
+
"model.visual.blocks.15.attn.qkv",
|
| 109 |
+
"model.visual.blocks.15.attn.proj",
|
| 110 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 111 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 112 |
+
"model.visual.blocks.16.attn.qkv",
|
| 113 |
+
"model.visual.blocks.16.attn.proj",
|
| 114 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 115 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 116 |
+
"model.visual.blocks.17.attn.qkv",
|
| 117 |
+
"model.visual.blocks.17.attn.proj",
|
| 118 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 119 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 120 |
+
"model.visual.blocks.18.attn.qkv",
|
| 121 |
+
"model.visual.blocks.18.attn.proj",
|
| 122 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 123 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 124 |
+
"model.visual.blocks.19.attn.qkv",
|
| 125 |
+
"model.visual.blocks.19.attn.proj",
|
| 126 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 127 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 128 |
+
"model.visual.blocks.20.attn.qkv",
|
| 129 |
+
"model.visual.blocks.20.attn.proj",
|
| 130 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 131 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 132 |
+
"model.visual.blocks.21.attn.qkv",
|
| 133 |
+
"model.visual.blocks.21.attn.proj",
|
| 134 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 135 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 136 |
+
"model.visual.blocks.22.attn.qkv",
|
| 137 |
+
"model.visual.blocks.22.attn.proj",
|
| 138 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 139 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 140 |
+
"model.visual.blocks.23.attn.qkv",
|
| 141 |
+
"model.visual.blocks.23.attn.proj",
|
| 142 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 143 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 144 |
+
"model.visual.blocks.24.attn.qkv",
|
| 145 |
+
"model.visual.blocks.24.attn.proj",
|
| 146 |
+
"model.visual.blocks.24.mlp.linear_fc1",
|
| 147 |
+
"model.visual.blocks.24.mlp.linear_fc2",
|
| 148 |
+
"model.visual.blocks.25.attn.qkv",
|
| 149 |
+
"model.visual.blocks.25.attn.proj",
|
| 150 |
+
"model.visual.blocks.25.mlp.linear_fc1",
|
| 151 |
+
"model.visual.blocks.25.mlp.linear_fc2",
|
| 152 |
+
"model.visual.blocks.26.attn.qkv",
|
| 153 |
+
"model.visual.blocks.26.attn.proj",
|
| 154 |
+
"model.visual.blocks.26.mlp.linear_fc1",
|
| 155 |
+
"model.visual.blocks.26.mlp.linear_fc2",
|
| 156 |
+
"model.visual.merger.linear_fc1",
|
| 157 |
+
"model.visual.merger.linear_fc2",
|
| 158 |
+
"model.visual.deepstack_merger_list.0.linear_fc1",
|
| 159 |
+
"model.visual.deepstack_merger_list.0.linear_fc2",
|
| 160 |
+
"model.visual.deepstack_merger_list.1.linear_fc1",
|
| 161 |
+
"model.visual.deepstack_merger_list.1.linear_fc2",
|
| 162 |
+
"model.visual.deepstack_merger_list.2.linear_fc1",
|
| 163 |
+
"model.visual.deepstack_merger_list.2.linear_fc2",
|
| 164 |
+
"lm_head"
|
| 165 |
+
],
|
| 166 |
+
"kv_cache_scheme": null,
|
| 167 |
+
"quant_method": "compressed-tensors",
|
| 168 |
+
"quantization_status": "compressed",
|
| 169 |
+
"sparsity_config": {},
|
| 170 |
+
"transform_config": {},
|
| 171 |
+
"version": "0.11.1.dev30+g3e4d7fa"
|
| 172 |
+
},
|
| 173 |
+
"text_config": {
|
| 174 |
+
"attention_bias": false,
|
| 175 |
+
"attention_dropout": 0.0,
|
| 176 |
+
"bos_token_id": 151643,
|
| 177 |
+
"decoder_sparse_step": 1,
|
| 178 |
+
"dtype": "bfloat16",
|
| 179 |
+
"eos_token_id": 151645,
|
| 180 |
+
"head_dim": 128,
|
| 181 |
+
"hidden_act": "silu",
|
| 182 |
+
"hidden_size": 4096,
|
| 183 |
+
"initializer_range": 0.02,
|
| 184 |
+
"intermediate_size": 12288,
|
| 185 |
+
"max_position_embeddings": 262144,
|
| 186 |
+
"mlp_only_layers": [],
|
| 187 |
+
"model_type": "qwen3_vl_moe_text",
|
| 188 |
+
"moe_intermediate_size": 1536,
|
| 189 |
+
"norm_topk_prob": true,
|
| 190 |
+
"num_attention_heads": 64,
|
| 191 |
+
"num_experts": 128,
|
| 192 |
+
"num_experts_per_tok": 8,
|
| 193 |
+
"num_hidden_layers": 94,
|
| 194 |
+
"num_key_value_heads": 4,
|
| 195 |
+
"rms_norm_eps": 1e-06,
|
| 196 |
+
"rope_scaling": {
|
| 197 |
+
"mrope_interleaved": true,
|
| 198 |
+
"mrope_section": [
|
| 199 |
+
24,
|
| 200 |
+
20,
|
| 201 |
+
20
|
| 202 |
+
],
|
| 203 |
+
"rope_type": "default"
|
| 204 |
+
},
|
| 205 |
+
"rope_theta": 5000000,
|
| 206 |
+
"use_cache": true,
|
| 207 |
+
"vocab_size": 151936
|
| 208 |
+
},
|
| 209 |
+
"tie_word_embeddings": false,
|
| 210 |
+
"transformers_version": "4.57.0.dev0",
|
| 211 |
+
"video_token_id": 151656,
|
| 212 |
+
"vision_config": {
|
| 213 |
+
"deepstack_visual_indexes": [
|
| 214 |
+
8,
|
| 215 |
+
16,
|
| 216 |
+
24
|
| 217 |
+
],
|
| 218 |
+
"depth": 27,
|
| 219 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 220 |
+
"hidden_size": 1152,
|
| 221 |
+
"in_channels": 3,
|
| 222 |
+
"initializer_range": 0.02,
|
| 223 |
+
"intermediate_size": 4304,
|
| 224 |
+
"model_type": "qwen3_vl_moe",
|
| 225 |
+
"num_heads": 16,
|
| 226 |
+
"num_position_embeddings": 2304,
|
| 227 |
+
"out_hidden_size": 4096,
|
| 228 |
+
"patch_size": 16,
|
| 229 |
+
"spatial_merge_size": 2,
|
| 230 |
+
"temporal_patch_size": 2
|
| 231 |
+
},
|
| 232 |
+
"vision_end_token_id": 151653,
|
| 233 |
+
"vision_start_token_id": 151652
|
| 234 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_p": 0.8,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"repetition_penalty": 1.0,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aee02bfa2561f2014b513f5733cc6888f8253c7ddc95e7921a76c6bf443b522
|
| 3 |
+
size 4996296120
|
model-00002-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:699c749c19c4e3155ae33d0d398e06707c631065aee2ae6caeb301127c8577d6
|
| 3 |
+
size 4996274904
|
model-00004-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6607517f56d0c60bb52c25204485b35773dd66f40e3c16d21f19739775fef678
|
| 3 |
+
size 4996274912
|
model-00006-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36a441e5f0838f579a5f836f090d551c68756740ee0976f1760c7708bb922c91
|
| 3 |
+
size 4996276496
|
model-00007-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a9f88835da948194749cec3da517791c7b2d9547f02f175a156f8b792f7fd9d
|
| 3 |
+
size 4996276496
|
model-00008-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4fb7dd4fe2a9a5b5eb9eb97a977275e72bfabe3721cc9c956da116ef527dcde
|
| 3 |
+
size 4996276504
|
model-00009-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2a257b04553bbf199961080f8dfbe706ff9e050a5cbb491f70e361a66f9480
|
| 3 |
+
size 4996276512
|
model-00010-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a2fa4754dbaa32c411f1b7ecf6600417a7e9226c4bb73e678f5749ac678226
|
| 3 |
+
size 4996276520
|
model-00011-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65104857ce48c838eaf31d112169ce28efb437b7e8b5a923a011ab9a29311c12
|
| 3 |
+
size 4996276528
|
model-00012-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c89078515c831524f5ae78afac479884c04a18637a3b65a73118f99e25ea436
|
| 3 |
+
size 4996276536
|
model-00013-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b6875d47a76d7a9ade14002e625d7465a07f0c0fc68ab76e1f6c4f26801d228
|
| 3 |
+
size 4996276544
|
model-00015-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b308c6619461e393bffbc9019be2dc97c4a444ab91dabc4da843a4a4e6adae50
|
| 3 |
+
size 4996276552
|
model-00021-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eee1bbd91ff105925034d50699e1b6f732f0d801677ea27893a928c8055732f
|
| 3 |
+
size 4996276592
|
model-00022-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b483916340b0f4f8cea68b58ddb88e72495d75035f8dc35dcffa1a083eca7726
|
| 3 |
+
size 4996276592
|
model-00023-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0215437a66871e781644550c71ceedbee04c636d96361863dce8a35a834ea8c
|
| 3 |
+
size 4996276600
|
model-00024-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:795f0614f8579f5e1081f2da99192d7d65843fb181f177c2bf9f24b3728f166b
|
| 3 |
+
size 4996276608
|
model-00025-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a10b7888188f54b039788b7ab9932d68df48179374befd76ea189f33d4403c
|
| 3 |
+
size 4996276616
|
model-00026-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13c0035ebd68198774e462f930e14fc93defa4e24c5255ec39511ecfda2600c3
|
| 3 |
+
size 4996276616
|
model-00027-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb598a4cef119802d90b3efca9f8faa88ca309b811cce01b16e5f58341cb8b52
|
| 3 |
+
size 4996276624
|
model-00028-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8a53439e3487fde56252e782970dda9ee7569fc080d419b83cc250f9b4d32cb
|
| 3 |
+
size 4996276632
|
model-00029-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc040bae803b489ff7f4faf3649eeb9012a346db1f5cbddb2f711ca1d72eae6
|
| 3 |
+
size 4996276640
|
model-00030-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8bc1cf784160787748b21d853ac2e32bfe28c923fe8a6b471e4fca785b72dd7
|
| 3 |
+
size 4996276640
|
model-00031-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:911ec2e15dfc082b77e2bc94c27d9b5514b9d92ee7f7470edabd402a3f3b2e40
|
| 3 |
+
size 4996276648
|
model-00033-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecdc66c635b184caaeabd2e60cc500b598b90ee817696b4dcc45d82054edf922
|
| 3 |
+
size 4996276664
|
model-00034-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ede1bb254c1d95fbca4e4db1798ffbe41906d4d14f3d37f577888c8c4953180
|
| 3 |
+
size 4996276664
|
model-00035-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc8c3593c0df9258cbdd115b5271d65013aed2f1d79a67908411ecf3e5d7f0d4
|
| 3 |
+
size 4996276672
|
model-00036-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec0835b56440ede9afc70aff76afbb0f9e045273964f639a9a30328ef08d5324
|
| 3 |
+
size 4996276680
|
model-00037-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fba5fdbcdc7bd49db7ca04a363010f424181eee1d639c1535c2466592685d147
|
| 3 |
+
size 4996276688
|
model-00038-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2837f1c2c4b356e50f5ed6170aecc0b8dc24837dcf78394b1364fea76e7dded4
|
| 3 |
+
size 4996276688
|
model-00041-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a60af4f4fb48556de4f00339fb68680a21b71c73e28c4a964ef5ede96e01b0f2
|
| 3 |
+
size 4996276712
|
model-00042-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6de3ebc3f3e192e02cb42f9e2eb6f400f3dbb2f07c699ff3d5f15c020fdd00f
|
| 3 |
+
size 4996276712
|
model-00043-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa1d00f417cd41878fbf0d4799e0b12e17b2e91a9beac729cf9e0960fcc83acf
|
| 3 |
+
size 4996276720
|
model-00044-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:202848348b9ed6200131a06fa3dc0c2c2b26d9490b78a32fb0fd053195ca67b9
|
| 3 |
+
size 4996276728
|
model-00045-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdf7947e7a75ea83bd2e8df92c1c855f1c97f527f5fe1d32314aa95386810891
|
| 3 |
+
size 4996276736
|
model-00046-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18dcfe3d0f3c61b633c8e5464591bbb2a1e0a2afe4a6ac8618b9b739339d8882
|
| 3 |
+
size 4996276736
|
model-00047-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8ae5c08ebdd449aca3dae9a6df63f91e1d690b3152212f5646d095013acc5b1
|
| 3 |
+
size 4996276744
|
model-00048-of-00048.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d35b3c090229f06ee96407f9c77c7fc577a7b524158fcbd2c9a84b26881a57c
|
| 3 |
+
size 2754887272
|
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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: ['re:.*lm_head', 're:.*router', 're:visual.*', 're:model.visual.*', 're:.*mlp.gate$',
|
| 6 |
+
're:.*mlp.shared_expert_gate$', 're:multi_modal_projector.*']
|
| 7 |
+
scheme: FP8_BLOCK
|
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 |
+
}
|