Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5
unsloth
fine tune
all use cases
coder
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
bfloat16
conversational
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +163 -0
- config.json +174 -0
- model-00001-of-00017.safetensors +3 -0
- model-00002-of-00017.safetensors +3 -0
- model-00003-of-00017.safetensors +3 -0
- model-00004-of-00017.safetensors +3 -0
- model-00005-of-00017.safetensors +3 -0
- model-00006-of-00017.safetensors +3 -0
- model-00007-of-00017.safetensors +3 -0
- model-00008-of-00017.safetensors +3 -0
- model-00009-of-00017.safetensors +3 -0
- model-00010-of-00017.safetensors +3 -0
- model-00011-of-00017.safetensors +3 -0
- model-00012-of-00017.safetensors +3 -0
- model-00013-of-00017.safetensors +3 -0
- model-00014-of-00017.safetensors +3 -0
- model-00015-of-00017.safetensors +3 -0
- model-00016-of-00017.safetensors +3 -0
- model-00017-of-00017.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +21 -0
- processor_config.json +63 -0
- tokenizer.json +3 -0
- tokenizer_config.json +304 -0
- video_preprocessor_config.json +21 -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
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Define the macros for XML conversion #}
|
| 2 |
+
{%- macro render_item_list(item_list, tag_name='required') -%}
|
| 3 |
+
{%- if item_list is defined and item_list is iterable and item_list | length > 0 -%}
|
| 4 |
+
<{{ tag_name }}>[{{- item_list | join(", ") -}}]</{{ tag_name }}>
|
| 5 |
+
{%- endif -%}
|
| 6 |
+
{%- endmacro -%}
|
| 7 |
+
|
| 8 |
+
{%- macro render_extra_keys(json_dict, handled_keys) -%}
|
| 9 |
+
{%- if json_dict is mapping -%}
|
| 10 |
+
{%- for json_key in json_dict if json_key not in handled_keys -%}
|
| 11 |
+
<{{ json_key }}>{{ json_dict[json_key] }}</{{ json_key }}>
|
| 12 |
+
{%- endfor -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- endmacro -%}
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
{%- set image_count = namespace(value=0) %}
|
| 18 |
+
{%- set video_count = namespace(value=0) %}
|
| 19 |
+
{%- set add_vision_id = add_vision_id if add_vision_id is defined else true %}
|
| 20 |
+
|
| 21 |
+
{# Set Instruct mode here #}
|
| 22 |
+
|
| 23 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 24 |
+
{%- if content is string %}
|
| 25 |
+
{{- content }}
|
| 26 |
+
{%- elif content is iterable and content is not mapping %}
|
| 27 |
+
{%- for item in content %}
|
| 28 |
+
{%- if 'image' in item or 'image_url' in item or (item is mapping and item.get('type') == 'image') %}
|
| 29 |
+
{%- if is_system_content %}
|
| 30 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if do_vision_count %}
|
| 33 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- if add_vision_id %}
|
| 36 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 39 |
+
{%- elif 'video' in item or (item is mapping and item.get('type') == 'video') %}
|
| 40 |
+
{%- if is_system_content %}
|
| 41 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if do_vision_count %}
|
| 44 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{%- if add_vision_id %}
|
| 47 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 50 |
+
{%- elif item is mapping and 'text' in item %}
|
| 51 |
+
{{- item.text }}
|
| 52 |
+
{%- else %}
|
| 53 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{%- endfor %}
|
| 56 |
+
{%- elif content is none or content is undefined %}
|
| 57 |
+
{{- '' }}
|
| 58 |
+
{%- else %}
|
| 59 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 60 |
+
{%- endif %}
|
| 61 |
+
{%- endmacro %}
|
| 62 |
+
|
| 63 |
+
{%- if not messages %}
|
| 64 |
+
{{- raise_exception('No messages provided.') }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
|
| 67 |
+
{# Flag to prevent double-rendering system prompt #}
|
| 68 |
+
{%- set ns = namespace(system_rendered=false) %}
|
| 69 |
+
|
| 70 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 71 |
+
|
| 72 |
+
{{- '<|im_start|>system\n# Tools\n\nYou have access to the following functions:\n\n<tools>' -}}
|
| 73 |
+
{%- for tool in tools -%}
|
| 74 |
+
{%- set function = tool.function -%}
|
| 75 |
+
{{- "\n<tool>\n<name>" + function.name + "</name>\n<description>" + function.description + "</description>" -}}
|
| 76 |
+
{%- if function.parameters and function.parameters.properties -%}
|
| 77 |
+
{%- for param_name, param_details in function.parameters.properties.items() -%}
|
| 78 |
+
{{- "\n<parameter>\n<name>" + param_name + "</name>\n<type>" + param_details.type + "</type>\n<description>" + (param_details.description | default('')) + "</description>" -}}
|
| 79 |
+
{{- render_item_list(function.parameters.required) -}}
|
| 80 |
+
{{- render_extra_keys(param_details, ['type', 'description']) -}}
|
| 81 |
+
{{- "\n</parameter>" -}}
|
| 82 |
+
{%- endfor -%}
|
| 83 |
+
{%- endif -%}
|
| 84 |
+
{{- "\n</tool>" -}}
|
| 85 |
+
{%- endfor -%}
|
| 86 |
+
|
| 87 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 88 |
+
|
| 89 |
+
{%- if messages[0].role == 'system' %}
|
| 90 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 91 |
+
{%- if content %}
|
| 92 |
+
{{- '\n\n' + content }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{%- set ns.system_rendered = true %}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{{- '<|im_end|>\n' }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- if messages[0].role == 'system' %}
|
| 99 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 100 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 101 |
+
{%- set ns.system_rendered = true %}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{%- endif %}
|
| 104 |
+
|
| 105 |
+
{# Main Message Loop #}
|
| 106 |
+
{%- for message in messages %}
|
| 107 |
+
{%- if message.role == "system" and ns.system_rendered and loop.first %}
|
| 108 |
+
{%- continue %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
|
| 111 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 112 |
+
|
| 113 |
+
{%- if message.role == "system" %}
|
| 114 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 115 |
+
{%- elif message.role == "user" %}
|
| 116 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' }}
|
| 117 |
+
{%- elif message.role == "assistant" %}
|
| 118 |
+
{%- set reasoning_content = '' %}
|
| 119 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is string %}
|
| 120 |
+
{%- set reasoning_content = message.reasoning_content | trim %}
|
| 121 |
+
{%- elif '<think>' in content and '</think>' in content %}
|
| 122 |
+
{%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] | trim %}
|
| 123 |
+
{%- set content = content.split('</think>')[-1] | trim %}
|
| 124 |
+
{%- endif %}
|
| 125 |
+
|
| 126 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 127 |
+
|
| 128 |
+
{%- if reasoning_content %}
|
| 129 |
+
{{- '<think>\n' + reasoning_content + '\n</think>\n\n' }}
|
| 130 |
+
{%- endif %}
|
| 131 |
+
|
| 132 |
+
{{- content }}
|
| 133 |
+
|
| 134 |
+
{# Tool call formatting #}
|
| 135 |
+
{%- if message.tool_calls %}
|
| 136 |
+
{%- for tool_call in message.tool_calls %}
|
| 137 |
+
{%- set tc = tool_call.function if tool_call.function is defined else tool_call %}
|
| 138 |
+
{%- if loop.first and content %}{{- '\n\n' }}{%- elif not loop.first %}{{- '\n' }}{%- endif %}
|
| 139 |
+
{{- '<tool_call>\n<function=' + tc.name + '>\n' }}
|
| 140 |
+
{%- for args_name, args_value in tc.arguments|items %}
|
| 141 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 142 |
+
{{- (args_value | tojson | safe if args_value is mapping or args_value is sequence else args_value | string) + '\n</parameter>\n' }}
|
| 143 |
+
{%- endfor %}
|
| 144 |
+
{{- '</function>\n</tool_call>' }}
|
| 145 |
+
{%- endfor %}
|
| 146 |
+
{%- endif %}
|
| 147 |
+
{{- '<|im_end|>\n' }}
|
| 148 |
+
{%- elif message.role == "tool" %}
|
| 149 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}{{- '<|im_start|>user' }}{%- endif %}
|
| 150 |
+
{{- '\n<tool_response>\n' + content + '\n</tool_response>' }}
|
| 151 |
+
{%- if loop.last or (loop.nextitem and loop.nextitem.role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}
|
| 152 |
+
{%- endif %}
|
| 153 |
+
{%- endfor %}
|
| 154 |
+
|
| 155 |
+
{# Final Generation Prompt #}
|
| 156 |
+
{%- if add_generation_prompt %}
|
| 157 |
+
{{- '<|im_start|>assistant\n' }}
|
| 158 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 159 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 160 |
+
{%- else %}
|
| 161 |
+
{{- '<think>\n' }}
|
| 162 |
+
{%- endif %}
|
| 163 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"torch_dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 248056,
|
| 7 |
+
"model_type": "qwen3_5",
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"text_config": {
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"attn_output_gate": true,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"torch_dtype": "bfloat16",
|
| 15 |
+
"eos_token_id": 248044,
|
| 16 |
+
"full_attention_interval": 4,
|
| 17 |
+
"head_dim": 256,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 5120,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 17408,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"linear_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"linear_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"linear_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"linear_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"linear_attention",
|
| 82 |
+
"full_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"linear_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"linear_attention",
|
| 90 |
+
"full_attention",
|
| 91 |
+
"linear_attention",
|
| 92 |
+
"linear_attention",
|
| 93 |
+
"linear_attention",
|
| 94 |
+
"full_attention",
|
| 95 |
+
"linear_attention",
|
| 96 |
+
"linear_attention",
|
| 97 |
+
"linear_attention",
|
| 98 |
+
"full_attention",
|
| 99 |
+
"linear_attention",
|
| 100 |
+
"linear_attention",
|
| 101 |
+
"linear_attention",
|
| 102 |
+
"full_attention",
|
| 103 |
+
"linear_attention",
|
| 104 |
+
"linear_attention",
|
| 105 |
+
"linear_attention",
|
| 106 |
+
"full_attention",
|
| 107 |
+
"linear_attention",
|
| 108 |
+
"linear_attention",
|
| 109 |
+
"linear_attention",
|
| 110 |
+
"full_attention",
|
| 111 |
+
"linear_attention",
|
| 112 |
+
"linear_attention",
|
| 113 |
+
"linear_attention",
|
| 114 |
+
"full_attention",
|
| 115 |
+
"linear_attention",
|
| 116 |
+
"linear_attention",
|
| 117 |
+
"linear_attention",
|
| 118 |
+
"full_attention"
|
| 119 |
+
],
|
| 120 |
+
"linear_conv_kernel_dim": 4,
|
| 121 |
+
"linear_key_head_dim": 128,
|
| 122 |
+
"linear_num_key_heads": 16,
|
| 123 |
+
"linear_num_value_heads": 48,
|
| 124 |
+
"linear_value_head_dim": 128,
|
| 125 |
+
"mamba_ssm_dtype": "float32",
|
| 126 |
+
"max_position_embeddings": 262144,
|
| 127 |
+
"mlp_only_layers": [],
|
| 128 |
+
"model_type": "qwen3_5_text",
|
| 129 |
+
"mtp_num_hidden_layers": 1,
|
| 130 |
+
"mtp_use_dedicated_embeddings": false,
|
| 131 |
+
"num_attention_heads": 24,
|
| 132 |
+
"num_hidden_layers": 96,
|
| 133 |
+
"num_key_value_heads": 4,
|
| 134 |
+
"pad_token_id": null,
|
| 135 |
+
"partial_rotary_factor": 0.25,
|
| 136 |
+
"rms_norm_eps": 1e-06,
|
| 137 |
+
"rope_parameters": {
|
| 138 |
+
"mrope_interleaved": true,
|
| 139 |
+
"mrope_section": [
|
| 140 |
+
11,
|
| 141 |
+
11,
|
| 142 |
+
10
|
| 143 |
+
],
|
| 144 |
+
"partial_rotary_factor": 0.25,
|
| 145 |
+
"rope_theta": 10000000,
|
| 146 |
+
"rope_type": "default"
|
| 147 |
+
},
|
| 148 |
+
"tie_word_embeddings": false,
|
| 149 |
+
"use_cache": true,
|
| 150 |
+
"vocab_size": 248320
|
| 151 |
+
},
|
| 152 |
+
"tie_word_embeddings": false,
|
| 153 |
+
"unsloth_version": "2026.2.1",
|
| 154 |
+
"video_token_id": 248057,
|
| 155 |
+
"vision_config": {
|
| 156 |
+
"deepstack_visual_indexes": [],
|
| 157 |
+
"depth": 27,
|
| 158 |
+
"torch_dtype": "bfloat16",
|
| 159 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 160 |
+
"hidden_size": 1152,
|
| 161 |
+
"in_channels": 3,
|
| 162 |
+
"initializer_range": 0.02,
|
| 163 |
+
"intermediate_size": 4304,
|
| 164 |
+
"model_type": "qwen3_5",
|
| 165 |
+
"num_heads": 16,
|
| 166 |
+
"num_position_embeddings": 2304,
|
| 167 |
+
"out_hidden_size": 5120,
|
| 168 |
+
"patch_size": 16,
|
| 169 |
+
"spatial_merge_size": 2,
|
| 170 |
+
"temporal_patch_size": 2
|
| 171 |
+
},
|
| 172 |
+
"vision_end_token_id": 248054,
|
| 173 |
+
"vision_start_token_id": 248053
|
| 174 |
+
}
|
model-00001-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c1ebaabbaca559789304b32d41530fb890cb406d30b4113f2e0e754a05dc93d
|
| 3 |
+
size 2542796928
|
model-00002-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:768374b2d3ecbc63ee3153204cab3f477846f4c3bc8896e28616c452f27bdc33
|
| 3 |
+
size 4842451936
|
model-00003-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a63400dc71f28026ae8b67d43d42deec2cf525f1d90160df256fe725adfbf8d
|
| 3 |
+
size 4965217656
|
model-00004-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f91af76c559d73a885d362b2b779d2b54497a34f89562ef8b00da325286f2785
|
| 3 |
+
size 4912829672
|
model-00005-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4b6afb02dd57c18f11c61915c9c920ebc80c488ee0fc8123a7c39d361aa4df4
|
| 3 |
+
size 4829966416
|
model-00006-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60a0c25aaef56fbce1f35833e19fc2d7e8da2869dea5dae7c2f0f83cfb545ac9
|
| 3 |
+
size 4911732776
|
model-00007-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6246a00115e1db52136d7cea6eca9795307dc7849836bd3e1215471f43b32430
|
| 3 |
+
size 4945363240
|
model-00008-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf34987812e7b8951190104d2a807e98d1c383e4ed754f5edce3a10c998a0723
|
| 3 |
+
size 4941059704
|
model-00009-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aed978dd8dd8b0c7bee13a79cd5629cb9c1285e141b372b1d6c4d95fd4bedc1b
|
| 3 |
+
size 4924369080
|
model-00010-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e26d9e6212b3fc0c9ad559fe572b061200de92150beb23cf5e1528690d1ff61a
|
| 3 |
+
size 4840465248
|
model-00011-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08e4924ebff8f3c6f6f35e7f96debfac69007c026897e443d51e41af370e6fe2
|
| 3 |
+
size 4965247528
|
model-00012-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91566872066f685eb81872ac1853de0f6f59804c442490b51d07176922d5ddf5
|
| 3 |
+
size 4911733960
|
model-00013-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ede01010bba76b94e3117724300e7e411a7c86754aecf112ce9e59e0195db05
|
| 3 |
+
size 4848814856
|
model-00014-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4799e28b2299487b3fed34a2048bd13a9f8b2bfaffcc0e0c20eb78b656cfd4
|
| 3 |
+
size 4996697312
|
model-00015-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7be54f74027e4ee9ccc30e3b8ea57071c80fc333ebb0a7e1c78507f4a64274a2
|
| 3 |
+
size 4933789824
|
model-00016-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89510d4d4dd975c68aafacde2880f9fb178e6cefa31c2f7ac220dc3b11b63af2
|
| 3 |
+
size 4911732712
|
model-00017-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9f3b6d10a8d0d78ab092aa524930f7a8b05b825f766fb8250da396c156e6b68
|
| 3 |
+
size 3587132840
|
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 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "_Unsloth_Patched_Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
|
| 3 |
+
size 12807982
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"248044": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"248045": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"248046": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"248047": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"248048": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"248049": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"248050": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"248051": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"248052": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"248053": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"248054": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"248055": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"248056": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"248057": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"248058": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"248059": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"248060": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"248061": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"248062": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"248063": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"248064": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"248065": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"248066": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"248067": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"248068": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"248069": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"248070": {
|
| 213 |
+
"content": "<|audio_start|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"248071": {
|
| 221 |
+
"content": "<|audio_end|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"248072": {
|
| 229 |
+
"content": "<tts_pad>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"248073": {
|
| 237 |
+
"content": "<tts_text_bos>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"248074": {
|
| 245 |
+
"content": "<tts_text_eod>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"248075": {
|
| 253 |
+
"content": "<tts_text_bos_single>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"248076": {
|
| 261 |
+
"content": "<|audio_pad|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"additional_special_tokens": [
|
| 270 |
+
"<|im_start|>",
|
| 271 |
+
"<|im_end|>",
|
| 272 |
+
"<|object_ref_start|>",
|
| 273 |
+
"<|object_ref_end|>",
|
| 274 |
+
"<|box_start|>",
|
| 275 |
+
"<|box_end|>",
|
| 276 |
+
"<|quad_start|>",
|
| 277 |
+
"<|quad_end|>",
|
| 278 |
+
"<|vision_start|>",
|
| 279 |
+
"<|vision_end|>",
|
| 280 |
+
"<|vision_pad|>",
|
| 281 |
+
"<|image_pad|>",
|
| 282 |
+
"<|video_pad|>"
|
| 283 |
+
],
|
| 284 |
+
"bos_token": null,
|
| 285 |
+
"clean_up_tokenization_spaces": false,
|
| 286 |
+
"eos_token": "<|im_end|>",
|
| 287 |
+
"errors": "replace",
|
| 288 |
+
"model_max_length": 262144,
|
| 289 |
+
"pad_token": "<|endoftext|>",
|
| 290 |
+
"split_special_tokens": false,
|
| 291 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 292 |
+
"unk_token": null,
|
| 293 |
+
"add_bos_token": false,
|
| 294 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 295 |
+
"extra_special_tokens": {
|
| 296 |
+
"audio_bos_token": "<|audio_start|>",
|
| 297 |
+
"audio_eos_token": "<|audio_end|>",
|
| 298 |
+
"audio_token": "<|audio_pad|>",
|
| 299 |
+
"image_token": "<|image_pad|>",
|
| 300 |
+
"video_token": "<|video_pad|>",
|
| 301 |
+
"vision_bos_token": "<|vision_start|>",
|
| 302 |
+
"vision_eos_token": "<|vision_end|>"
|
| 303 |
+
}
|
| 304 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 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 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|