Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +154 -0
- config.json +289 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model.safetensors.index.json +0 -0
- mtp.safetensors +3 -0
- preprocessor_config.json +21 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -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 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\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>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 248056,
|
| 7 |
+
"language_model_only": false,
|
| 8 |
+
"model_type": "qwen3_5",
|
| 9 |
+
"quantization_config": {
|
| 10 |
+
"include_input_output_embeddings": false,
|
| 11 |
+
"modules_to_not_convert": [
|
| 12 |
+
"mtp",
|
| 13 |
+
"model.visual",
|
| 14 |
+
"model.visual.merger",
|
| 15 |
+
"model.visual.patch_embed",
|
| 16 |
+
"vision_tower",
|
| 17 |
+
"MoonViT",
|
| 18 |
+
"lm_head"
|
| 19 |
+
],
|
| 20 |
+
"quant_method": "torchao",
|
| 21 |
+
"quant_type": {
|
| 22 |
+
"default": {
|
| 23 |
+
"_data": {
|
| 24 |
+
"fqn_to_config": {
|
| 25 |
+
"_default": {
|
| 26 |
+
"_data": {
|
| 27 |
+
"activation_dtype": {
|
| 28 |
+
"_data": "float8_e4m3fn",
|
| 29 |
+
"_type": "torch.dtype"
|
| 30 |
+
},
|
| 31 |
+
"activation_value_lb": null,
|
| 32 |
+
"activation_value_ub": null,
|
| 33 |
+
"granularity": [
|
| 34 |
+
{
|
| 35 |
+
"_data": {
|
| 36 |
+
"dim": -1
|
| 37 |
+
},
|
| 38 |
+
"_type": "PerRow",
|
| 39 |
+
"_version": 1
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"_data": {
|
| 43 |
+
"dim": -1
|
| 44 |
+
},
|
| 45 |
+
"_type": "PerRow",
|
| 46 |
+
"_version": 1
|
| 47 |
+
}
|
| 48 |
+
],
|
| 49 |
+
"kernel_preference": {
|
| 50 |
+
"_data": "AUTO",
|
| 51 |
+
"_type": "KernelPreference"
|
| 52 |
+
},
|
| 53 |
+
"mm_config": {
|
| 54 |
+
"_data": {
|
| 55 |
+
"emulate": false,
|
| 56 |
+
"pad_inner_dim": false,
|
| 57 |
+
"use_fast_accum": true
|
| 58 |
+
},
|
| 59 |
+
"_type": "Float8MMConfig",
|
| 60 |
+
"_version": 1
|
| 61 |
+
},
|
| 62 |
+
"packing_format": {
|
| 63 |
+
"_data": "PLAIN",
|
| 64 |
+
"_type": "Float8PackingFormat"
|
| 65 |
+
},
|
| 66 |
+
"set_inductor_config": true,
|
| 67 |
+
"weight_dtype": {
|
| 68 |
+
"_data": "float8_e4m3fn",
|
| 69 |
+
"_type": "torch.dtype"
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"_type": "Float8DynamicActivationFloat8WeightConfig",
|
| 73 |
+
"_version": 2
|
| 74 |
+
},
|
| 75 |
+
"re:.*MoonViT.*": null,
|
| 76 |
+
"re:.*\\.merger\\..*": null,
|
| 77 |
+
"re:.*\\.mtp\\..*": null,
|
| 78 |
+
"re:.*\\.vision_tower\\..*": null,
|
| 79 |
+
"re:.*\\.visual\\..*": null,
|
| 80 |
+
"re:.*nextn.*": null,
|
| 81 |
+
"re:^lm_head$": null,
|
| 82 |
+
"re:^lm_head\\..*": null,
|
| 83 |
+
"re:^model\\.visual\\..*": null,
|
| 84 |
+
"re:^mtp\\..*": null
|
| 85 |
+
},
|
| 86 |
+
"module_fqn_to_config": {
|
| 87 |
+
"_default": {
|
| 88 |
+
"_data": {
|
| 89 |
+
"activation_dtype": {
|
| 90 |
+
"_data": "float8_e4m3fn",
|
| 91 |
+
"_type": "torch.dtype"
|
| 92 |
+
},
|
| 93 |
+
"activation_value_lb": null,
|
| 94 |
+
"activation_value_ub": null,
|
| 95 |
+
"granularity": [
|
| 96 |
+
{
|
| 97 |
+
"_data": {
|
| 98 |
+
"dim": -1
|
| 99 |
+
},
|
| 100 |
+
"_type": "PerRow",
|
| 101 |
+
"_version": 1
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"_data": {
|
| 105 |
+
"dim": -1
|
| 106 |
+
},
|
| 107 |
+
"_type": "PerRow",
|
| 108 |
+
"_version": 1
|
| 109 |
+
}
|
| 110 |
+
],
|
| 111 |
+
"kernel_preference": {
|
| 112 |
+
"_data": "AUTO",
|
| 113 |
+
"_type": "KernelPreference"
|
| 114 |
+
},
|
| 115 |
+
"mm_config": {
|
| 116 |
+
"_data": {
|
| 117 |
+
"emulate": false,
|
| 118 |
+
"pad_inner_dim": false,
|
| 119 |
+
"use_fast_accum": true
|
| 120 |
+
},
|
| 121 |
+
"_type": "Float8MMConfig",
|
| 122 |
+
"_version": 1
|
| 123 |
+
},
|
| 124 |
+
"packing_format": {
|
| 125 |
+
"_data": "PLAIN",
|
| 126 |
+
"_type": "Float8PackingFormat"
|
| 127 |
+
},
|
| 128 |
+
"set_inductor_config": true,
|
| 129 |
+
"weight_dtype": {
|
| 130 |
+
"_data": "float8_e4m3fn",
|
| 131 |
+
"_type": "torch.dtype"
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"_type": "Float8DynamicActivationFloat8WeightConfig",
|
| 135 |
+
"_version": 2
|
| 136 |
+
},
|
| 137 |
+
"re:.*MoonViT.*": null,
|
| 138 |
+
"re:.*\\.merger\\..*": null,
|
| 139 |
+
"re:.*\\.mtp\\..*": null,
|
| 140 |
+
"re:.*\\.vision_tower\\..*": null,
|
| 141 |
+
"re:.*\\.visual\\..*": null,
|
| 142 |
+
"re:.*nextn.*": null,
|
| 143 |
+
"re:^lm_head$": null,
|
| 144 |
+
"re:^lm_head\\..*": null,
|
| 145 |
+
"re:^model\\.visual\\..*": null,
|
| 146 |
+
"re:^mtp\\..*": null
|
| 147 |
+
}
|
| 148 |
+
},
|
| 149 |
+
"_type": "FqnToConfig",
|
| 150 |
+
"_version": 1
|
| 151 |
+
}
|
| 152 |
+
},
|
| 153 |
+
"untie_embedding_weights": false
|
| 154 |
+
},
|
| 155 |
+
"text_config": {
|
| 156 |
+
"attention_bias": false,
|
| 157 |
+
"attention_dropout": 0.0,
|
| 158 |
+
"attn_output_gate": true,
|
| 159 |
+
"bos_token_id": 248044,
|
| 160 |
+
"dtype": "bfloat16",
|
| 161 |
+
"eos_token_id": 248044,
|
| 162 |
+
"full_attention_interval": 4,
|
| 163 |
+
"head_dim": 256,
|
| 164 |
+
"hidden_act": "silu",
|
| 165 |
+
"hidden_size": 5120,
|
| 166 |
+
"initializer_range": 0.02,
|
| 167 |
+
"intermediate_size": 17408,
|
| 168 |
+
"layer_types": [
|
| 169 |
+
"linear_attention",
|
| 170 |
+
"linear_attention",
|
| 171 |
+
"linear_attention",
|
| 172 |
+
"full_attention",
|
| 173 |
+
"linear_attention",
|
| 174 |
+
"linear_attention",
|
| 175 |
+
"linear_attention",
|
| 176 |
+
"full_attention",
|
| 177 |
+
"linear_attention",
|
| 178 |
+
"linear_attention",
|
| 179 |
+
"linear_attention",
|
| 180 |
+
"full_attention",
|
| 181 |
+
"linear_attention",
|
| 182 |
+
"linear_attention",
|
| 183 |
+
"linear_attention",
|
| 184 |
+
"full_attention",
|
| 185 |
+
"linear_attention",
|
| 186 |
+
"linear_attention",
|
| 187 |
+
"linear_attention",
|
| 188 |
+
"full_attention",
|
| 189 |
+
"linear_attention",
|
| 190 |
+
"linear_attention",
|
| 191 |
+
"linear_attention",
|
| 192 |
+
"full_attention",
|
| 193 |
+
"linear_attention",
|
| 194 |
+
"linear_attention",
|
| 195 |
+
"linear_attention",
|
| 196 |
+
"full_attention",
|
| 197 |
+
"linear_attention",
|
| 198 |
+
"linear_attention",
|
| 199 |
+
"linear_attention",
|
| 200 |
+
"full_attention",
|
| 201 |
+
"linear_attention",
|
| 202 |
+
"linear_attention",
|
| 203 |
+
"linear_attention",
|
| 204 |
+
"full_attention",
|
| 205 |
+
"linear_attention",
|
| 206 |
+
"linear_attention",
|
| 207 |
+
"linear_attention",
|
| 208 |
+
"full_attention",
|
| 209 |
+
"linear_attention",
|
| 210 |
+
"linear_attention",
|
| 211 |
+
"linear_attention",
|
| 212 |
+
"full_attention",
|
| 213 |
+
"linear_attention",
|
| 214 |
+
"linear_attention",
|
| 215 |
+
"linear_attention",
|
| 216 |
+
"full_attention",
|
| 217 |
+
"linear_attention",
|
| 218 |
+
"linear_attention",
|
| 219 |
+
"linear_attention",
|
| 220 |
+
"full_attention",
|
| 221 |
+
"linear_attention",
|
| 222 |
+
"linear_attention",
|
| 223 |
+
"linear_attention",
|
| 224 |
+
"full_attention",
|
| 225 |
+
"linear_attention",
|
| 226 |
+
"linear_attention",
|
| 227 |
+
"linear_attention",
|
| 228 |
+
"full_attention",
|
| 229 |
+
"linear_attention",
|
| 230 |
+
"linear_attention",
|
| 231 |
+
"linear_attention",
|
| 232 |
+
"full_attention"
|
| 233 |
+
],
|
| 234 |
+
"linear_conv_kernel_dim": 4,
|
| 235 |
+
"linear_key_head_dim": 128,
|
| 236 |
+
"linear_num_key_heads": 16,
|
| 237 |
+
"linear_num_value_heads": 48,
|
| 238 |
+
"linear_value_head_dim": 128,
|
| 239 |
+
"mamba_ssm_dtype": "float32",
|
| 240 |
+
"max_position_embeddings": 262144,
|
| 241 |
+
"model_type": "qwen3_5_text",
|
| 242 |
+
"mtp_num_hidden_layers": 1,
|
| 243 |
+
"mtp_use_dedicated_embeddings": false,
|
| 244 |
+
"num_attention_heads": 24,
|
| 245 |
+
"num_hidden_layers": 64,
|
| 246 |
+
"num_key_value_heads": 4,
|
| 247 |
+
"output_gate_type": "swish",
|
| 248 |
+
"pad_token_id": null,
|
| 249 |
+
"partial_rotary_factor": 0.25,
|
| 250 |
+
"rms_norm_eps": 1e-06,
|
| 251 |
+
"rope_parameters": {
|
| 252 |
+
"mrope_interleaved": true,
|
| 253 |
+
"mrope_section": [
|
| 254 |
+
11,
|
| 255 |
+
11,
|
| 256 |
+
10
|
| 257 |
+
],
|
| 258 |
+
"partial_rotary_factor": 0.25,
|
| 259 |
+
"rope_theta": 10000000,
|
| 260 |
+
"rope_type": "default"
|
| 261 |
+
},
|
| 262 |
+
"tie_word_embeddings": false,
|
| 263 |
+
"use_cache": true,
|
| 264 |
+
"vocab_size": 248320
|
| 265 |
+
},
|
| 266 |
+
"tie_word_embeddings": false,
|
| 267 |
+
"transformers_version": "5.8.0.dev0",
|
| 268 |
+
"video_token_id": 248057,
|
| 269 |
+
"vision_config": {
|
| 270 |
+
"deepstack_visual_indexes": [],
|
| 271 |
+
"depth": 27,
|
| 272 |
+
"dtype": "bfloat16",
|
| 273 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 274 |
+
"hidden_size": 1152,
|
| 275 |
+
"in_channels": 3,
|
| 276 |
+
"initializer_range": 0.02,
|
| 277 |
+
"intermediate_size": 4304,
|
| 278 |
+
"model_type": "qwen3_5_vision",
|
| 279 |
+
"num_heads": 16,
|
| 280 |
+
"num_position_embeddings": 2304,
|
| 281 |
+
"out_hidden_size": 5120,
|
| 282 |
+
"patch_size": 16,
|
| 283 |
+
"spatial_merge_size": 2,
|
| 284 |
+
"temporal_patch_size": 2
|
| 285 |
+
},
|
| 286 |
+
"vision_end_token_id": 248054,
|
| 287 |
+
"vision_start_token_id": 248053,
|
| 288 |
+
"mtp_num_hidden_layers": 1
|
| 289 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d73ef10a51a0f91d7ed357a3e701180ce7b53ada08c1b2f9e8b8e3bf409f742
|
| 3 |
+
size 30379266944
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mtp.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:700141f4155c69f9a536a6a36e6a85bc6fc4d2f2d89cb80e8b64a9004771202f
|
| 3 |
+
size 849400424
|
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 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"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+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
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
|
|
|