Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +32 -0
- chat_template.jinja +126 -0
- config.json +200 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +21 -0
- scheduler_config.json +18 -0
- special_tokens_map.json +35 -0
- tokenizer.json +3 -0
- tokenizer_config.json +276 -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 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</image_edit>": 151672,
|
| 3 |
+
"</image_gen>": 151670,
|
| 4 |
+
"</think>": 151668,
|
| 5 |
+
"</tool_call>": 151658,
|
| 6 |
+
"</tool_response>": 151666,
|
| 7 |
+
"<image_edit>": 151671,
|
| 8 |
+
"<image_gen>": 151669,
|
| 9 |
+
"<think>": 151667,
|
| 10 |
+
"<tool_call>": 151657,
|
| 11 |
+
"<tool_response>": 151665,
|
| 12 |
+
"<|box_end|>": 151649,
|
| 13 |
+
"<|box_start|>": 151648,
|
| 14 |
+
"<|endoftext|>": 151643,
|
| 15 |
+
"<|file_sep|>": 151664,
|
| 16 |
+
"<|fim_middle|>": 151660,
|
| 17 |
+
"<|fim_pad|>": 151662,
|
| 18 |
+
"<|fim_prefix|>": 151659,
|
| 19 |
+
"<|fim_suffix|>": 151661,
|
| 20 |
+
"<|im_end|>": 151645,
|
| 21 |
+
"<|im_start|>": 151644,
|
| 22 |
+
"<|image_pad|>": 151655,
|
| 23 |
+
"<|object_ref_end|>": 151647,
|
| 24 |
+
"<|object_ref_start|>": 151646,
|
| 25 |
+
"<|quad_end|>": 151651,
|
| 26 |
+
"<|quad_start|>": 151650,
|
| 27 |
+
"<|repo_name|>": 151663,
|
| 28 |
+
"<|video_pad|>": 151656,
|
| 29 |
+
"<|vision_end|>": 151653,
|
| 30 |
+
"<|vision_pad|>": 151654,
|
| 31 |
+
"<|vision_start|>": 151652
|
| 32 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{%- else %}
|
| 14 |
+
{{- "你是中国科学院磐石团队训练的 S1-Omni 统一架构多模态模型，具备多模态图像理解和生成能力。" }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{{- '\n\n' }}
|
| 17 |
+
{{- "# 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>" }}
|
| 18 |
+
{%- for tool in tools %}
|
| 19 |
+
{{- "\n" }}
|
| 20 |
+
{{- tool | tojson }}
|
| 21 |
+
{%- endfor %}
|
| 22 |
+
{{- "\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" }}
|
| 23 |
+
{%- else %}
|
| 24 |
+
{%- if messages[0].role == 'system' %}
|
| 25 |
+
{{- '<|im_start|>system\n' }}
|
| 26 |
+
{%- if messages[0].content is string %}
|
| 27 |
+
{{- messages[0].content }}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- for content in messages[0].content %}
|
| 30 |
+
{%- if 'text' in content %}
|
| 31 |
+
{{- content.text }}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{%- endfor %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<|im_end|>\n' }}
|
| 36 |
+
{%- else %}
|
| 37 |
+
{{- '<|im_start|>system\n' }}
|
| 38 |
+
{{- "你是中国科学院磐石团队训练的 S1-Omni 统一架构多模态模型，具备多模态图像理解和生成能力。" }}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- set image_count = namespace(value=0) %}
|
| 43 |
+
{%- set video_count = namespace(value=0) %}
|
| 44 |
+
{%- for message in messages %}
|
| 45 |
+
{%- if message.role == "user" %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 47 |
+
{%- if message.content is string %}
|
| 48 |
+
{{- message.content }}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{%- for content in message.content %}
|
| 51 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 52 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 53 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 54 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 55 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 56 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 57 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 58 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 59 |
+
{%- elif 'text' in content %}
|
| 60 |
+
{{- content.text }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endfor %}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '<|im_end|>\n' }}
|
| 65 |
+
{%- elif message.role == "assistant" %}
|
| 66 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 67 |
+
{%- if message.content is string %}
|
| 68 |
+
{{- message.content }}
|
| 69 |
+
{%- else %}
|
| 70 |
+
{%- for content_item in message.content %}
|
| 71 |
+
{%- if 'text' in content_item %}
|
| 72 |
+
{{- content_item.text }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endfor %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- if message.tool_calls %}
|
| 77 |
+
{%- for tool_call in message.tool_calls %}
|
| 78 |
+
{%- if (loop.first and message.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 |
+
{%- if message.content is string %}
|
| 102 |
+
{{- message.content }}
|
| 103 |
+
{%- else %}
|
| 104 |
+
{%- for content in message.content %}
|
| 105 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 106 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 107 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 108 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 109 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 110 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 111 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 112 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 113 |
+
{%- elif 'text' in content %}
|
| 114 |
+
{{- content.text }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endfor %}
|
| 117 |
+
{%- endif %}
|
| 118 |
+
{{- '\n</tool_response>' }}
|
| 119 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 120 |
+
{{- '<|im_end|>\n' }}
|
| 121 |
+
{%- endif %}
|
| 122 |
+
{%- endif %}
|
| 123 |
+
{%- endfor %}
|
| 124 |
+
{%- if add_generation_prompt %}
|
| 125 |
+
{{- '<|im_start|>assistant\n' }}
|
| 126 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,200 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "s1-omni-image",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"S1OmniImageModel"
|
| 5 |
+
],
|
| 6 |
+
"prefixes": {
|
| 7 |
+
"qwen3_vl": "qwen3_vl.",
|
| 8 |
+
"transformer": "transformer.",
|
| 9 |
+
"vae": "vae.",
|
| 10 |
+
"alignment_mlp": "alignment_mlp."
|
| 11 |
+
},
|
| 12 |
+
"qwen3_vl_config": {
|
| 13 |
+
"architectures": [
|
| 14 |
+
"Qwen3VLForConditionalGeneration"
|
| 15 |
+
],
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 151645,
|
| 18 |
+
"hidden_size": 4096,
|
| 19 |
+
"image_token_id": 151655,
|
| 20 |
+
"model_type": "qwen3_vl",
|
| 21 |
+
"pad_token_id": 151643,
|
| 22 |
+
"text_config": {
|
| 23 |
+
"attention_bias": false,
|
| 24 |
+
"attention_dropout": 0.0,
|
| 25 |
+
"bos_token_id": 151643,
|
| 26 |
+
"dtype": "bfloat16",
|
| 27 |
+
"eos_token_id": 151645,
|
| 28 |
+
"head_dim": 128,
|
| 29 |
+
"hidden_act": "silu",
|
| 30 |
+
"hidden_size": 4096,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 12288,
|
| 33 |
+
"max_position_embeddings": 262144,
|
| 34 |
+
"model_type": "qwen3_vl_text",
|
| 35 |
+
"num_attention_heads": 32,
|
| 36 |
+
"num_hidden_layers": 36,
|
| 37 |
+
"num_key_value_heads": 8,
|
| 38 |
+
"pad_token_id": 151643,
|
| 39 |
+
"rms_norm_eps": 1e-06,
|
| 40 |
+
"rope_scaling": {
|
| 41 |
+
"mrope_interleaved": true,
|
| 42 |
+
"mrope_section": [
|
| 43 |
+
24,
|
| 44 |
+
20,
|
| 45 |
+
20
|
| 46 |
+
],
|
| 47 |
+
"rope_type": "default"
|
| 48 |
+
},
|
| 49 |
+
"rope_theta": 5000000,
|
| 50 |
+
"use_cache": false,
|
| 51 |
+
"vocab_size": 151936
|
| 52 |
+
},
|
| 53 |
+
"tie_word_embeddings": false,
|
| 54 |
+
"transformers_version": "4.57.6",
|
| 55 |
+
"video_token_id": 151656,
|
| 56 |
+
"vision_config": {
|
| 57 |
+
"deepstack_visual_indexes": [
|
| 58 |
+
8,
|
| 59 |
+
16,
|
| 60 |
+
24
|
| 61 |
+
],
|
| 62 |
+
"depth": 27,
|
| 63 |
+
"dtype": "bfloat16",
|
| 64 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 65 |
+
"hidden_size": 1152,
|
| 66 |
+
"in_channels": 3,
|
| 67 |
+
"initializer_range": 0.02,
|
| 68 |
+
"intermediate_size": 4304,
|
| 69 |
+
"model_type": "qwen3_vl",
|
| 70 |
+
"num_heads": 16,
|
| 71 |
+
"num_position_embeddings": 2304,
|
| 72 |
+
"out_hidden_size": 4096,
|
| 73 |
+
"pad_token_id": 151643,
|
| 74 |
+
"patch_size": 16,
|
| 75 |
+
"spatial_merge_size": 2,
|
| 76 |
+
"temporal_patch_size": 2
|
| 77 |
+
},
|
| 78 |
+
"vision_end_token_id": 151653,
|
| 79 |
+
"vision_start_token_id": 151652
|
| 80 |
+
},
|
| 81 |
+
"transformer_config": {
|
| 82 |
+
"_class_name": "QwenImageTransformer2DModel",
|
| 83 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 84 |
+
"attention_head_dim": 128,
|
| 85 |
+
"axes_dims_rope": [
|
| 86 |
+
16,
|
| 87 |
+
56,
|
| 88 |
+
56
|
| 89 |
+
],
|
| 90 |
+
"guidance_embeds": false,
|
| 91 |
+
"in_channels": 64,
|
| 92 |
+
"joint_attention_dim": 3584,
|
| 93 |
+
"num_attention_heads": 24,
|
| 94 |
+
"num_layers": 60,
|
| 95 |
+
"out_channels": 16,
|
| 96 |
+
"patch_size": 2,
|
| 97 |
+
"zero_cond_t": true
|
| 98 |
+
},
|
| 99 |
+
"vae_config": {
|
| 100 |
+
"_class_name": "AutoencoderKLQwenImage",
|
| 101 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 102 |
+
"attn_scales": [],
|
| 103 |
+
"base_dim": 96,
|
| 104 |
+
"dim_mult": [
|
| 105 |
+
1,
|
| 106 |
+
2,
|
| 107 |
+
4,
|
| 108 |
+
4
|
| 109 |
+
],
|
| 110 |
+
"dropout": 0.0,
|
| 111 |
+
"latents_mean": [
|
| 112 |
+
-0.7571,
|
| 113 |
+
-0.7089,
|
| 114 |
+
-0.9113,
|
| 115 |
+
0.1075,
|
| 116 |
+
-0.1745,
|
| 117 |
+
0.9653,
|
| 118 |
+
-0.1517,
|
| 119 |
+
1.5508,
|
| 120 |
+
0.4134,
|
| 121 |
+
-0.0715,
|
| 122 |
+
0.5517,
|
| 123 |
+
-0.3632,
|
| 124 |
+
-0.1922,
|
| 125 |
+
-0.9497,
|
| 126 |
+
0.2503,
|
| 127 |
+
-0.2921
|
| 128 |
+
],
|
| 129 |
+
"latents_std": [
|
| 130 |
+
2.8184,
|
| 131 |
+
1.4541,
|
| 132 |
+
2.3275,
|
| 133 |
+
2.6558,
|
| 134 |
+
1.2196,
|
| 135 |
+
1.7708,
|
| 136 |
+
2.6052,
|
| 137 |
+
2.0743,
|
| 138 |
+
3.2687,
|
| 139 |
+
2.1526,
|
| 140 |
+
2.8652,
|
| 141 |
+
1.5579,
|
| 142 |
+
1.6382,
|
| 143 |
+
1.1253,
|
| 144 |
+
2.8251,
|
| 145 |
+
1.916
|
| 146 |
+
],
|
| 147 |
+
"num_res_blocks": 2,
|
| 148 |
+
"temperal_downsample": [
|
| 149 |
+
false,
|
| 150 |
+
true,
|
| 151 |
+
true
|
| 152 |
+
],
|
| 153 |
+
"z_dim": 16
|
| 154 |
+
},
|
| 155 |
+
"scheduler_config": {
|
| 156 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 157 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 158 |
+
"base_image_seq_len": 256,
|
| 159 |
+
"base_shift": 0.5,
|
| 160 |
+
"invert_sigmas": false,
|
| 161 |
+
"max_image_seq_len": 8192,
|
| 162 |
+
"max_shift": 0.9,
|
| 163 |
+
"num_train_timesteps": 1000,
|
| 164 |
+
"shift": 1.0,
|
| 165 |
+
"shift_terminal": 0.02,
|
| 166 |
+
"stochastic_sampling": false,
|
| 167 |
+
"time_shift_type": "exponential",
|
| 168 |
+
"use_beta_sigmas": false,
|
| 169 |
+
"use_dynamic_shifting": true,
|
| 170 |
+
"use_exponential_sigmas": false,
|
| 171 |
+
"use_karras_sigmas": false
|
| 172 |
+
},
|
| 173 |
+
"alignment_mlp": {
|
| 174 |
+
"input_dim": 4096,
|
| 175 |
+
"output_dim": 3584,
|
| 176 |
+
"hidden_dim": 4096,
|
| 177 |
+
"type": "mlp"
|
| 178 |
+
},
|
| 179 |
+
"special_tokens": {
|
| 180 |
+
"think_start": "<think>",
|
| 181 |
+
"think_end": "</think>",
|
| 182 |
+
"image_gen_start": "<image_gen>",
|
| 183 |
+
"image_gen_end": "</image_gen>",
|
| 184 |
+
"image_edit_start": "<image_edit>",
|
| 185 |
+
"image_edit_end": "</image_edit>"
|
| 186 |
+
},
|
| 187 |
+
"generation": {
|
| 188 |
+
"max_new_tokens": 2048,
|
| 189 |
+
"temperature": 0.7,
|
| 190 |
+
"top_p": 0.9,
|
| 191 |
+
"do_sample": true
|
| 192 |
+
},
|
| 193 |
+
"image_generation": {
|
| 194 |
+
"default_height": 1024,
|
| 195 |
+
"default_width": 1024,
|
| 196 |
+
"num_inference_steps": 50,
|
| 197 |
+
"guidance_scale": 1.0,
|
| 198 |
+
"true_cfg_scale": 4.0
|
| 199 |
+
}
|
| 200 |
+
}
|
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 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.6"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36dc35adaeb30873fa7dbdd3c26ec5c184e71a009190b6afe6bfda3a03a8a6c5
|
| 3 |
+
size 10702597616
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9d0d101608c46f664a3d45a98967a91b42eb74b967389ac1cbc49f13bf5224b
|
| 3 |
+
size 10666324200
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d09697d3865f12ea6599a2156a96192b840938be80e16fd63fc1f11f7614410d
|
| 3 |
+
size 10707895576
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96d183a9edbacb1603d26218a7789a8ecc6575152256774c4222ffb4cafa8bd6
|
| 3 |
+
size 10723622400
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f3e5149ed3dee715a9c658bd1ddc8b436cf93373b5d6f672da1746095e3697c
|
| 3 |
+
size 10685890504
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08ec0749ea68dd5d8be16db85359ba3606bbf895731d6de078afd9a3b480849b
|
| 3 |
+
size 5288736662
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
scheduler_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"base_image_seq_len": 256,
|
| 5 |
+
"base_shift": 0.5,
|
| 6 |
+
"invert_sigmas": false,
|
| 7 |
+
"max_image_seq_len": 8192,
|
| 8 |
+
"max_shift": 0.9,
|
| 9 |
+
"num_train_timesteps": 1000,
|
| 10 |
+
"shift": 1.0,
|
| 11 |
+
"shift_terminal": 0.02,
|
| 12 |
+
"stochastic_sampling": false,
|
| 13 |
+
"time_shift_type": "exponential",
|
| 14 |
+
"use_beta_sigmas": false,
|
| 15 |
+
"use_dynamic_shifting": true,
|
| 16 |
+
"use_exponential_sigmas": false,
|
| 17 |
+
"use_karras_sigmas": false
|
| 18 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<image_gen>",
|
| 17 |
+
"</image_gen>",
|
| 18 |
+
"<image_edit>",
|
| 19 |
+
"</image_edit>"
|
| 20 |
+
],
|
| 21 |
+
"eos_token": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de33aeb2f82db3da24f73f30668122b8eb99d50e1c19ab3ab3a5947e0945708f
|
| 3 |
+
size 11423410
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151669": {
|
| 214 |
+
"content": "<image_gen>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "</image_gen>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "<image_edit>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "</image_edit>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
}
|
| 245 |
+
},
|
| 246 |
+
"additional_special_tokens": [
|
| 247 |
+
"<|im_start|>",
|
| 248 |
+
"<|im_end|>",
|
| 249 |
+
"<|object_ref_start|>",
|
| 250 |
+
"<|object_ref_end|>",
|
| 251 |
+
"<|box_start|>",
|
| 252 |
+
"<|box_end|>",
|
| 253 |
+
"<|quad_start|>",
|
| 254 |
+
"<|quad_end|>",
|
| 255 |
+
"<|vision_start|>",
|
| 256 |
+
"<|vision_end|>",
|
| 257 |
+
"<|vision_pad|>",
|
| 258 |
+
"<|image_pad|>",
|
| 259 |
+
"<|video_pad|>",
|
| 260 |
+
"<image_gen>",
|
| 261 |
+
"</image_gen>",
|
| 262 |
+
"<image_edit>",
|
| 263 |
+
"</image_edit>"
|
| 264 |
+
],
|
| 265 |
+
"bos_token": null,
|
| 266 |
+
"clean_up_tokenization_spaces": false,
|
| 267 |
+
"eos_token": "<|im_end|>",
|
| 268 |
+
"errors": "replace",
|
| 269 |
+
"extra_special_tokens": {},
|
| 270 |
+
"model_max_length": 262144,
|
| 271 |
+
"pad_token": "<|endoftext|>",
|
| 272 |
+
"processor_class": "Qwen3VLProcessor",
|
| 273 |
+
"split_special_tokens": false,
|
| 274 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 275 |
+
"unk_token": null
|
| 276 |
+
}
|
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
|
|
|