Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- chat_template.jinja +154 -0
- config.json +142 -0
- model.safetensors-00001-of-00094.safetensors +3 -0
- model.safetensors-00002-of-00094.safetensors +3 -0
- model.safetensors-00003-of-00094.safetensors +3 -0
- model.safetensors-00004-of-00094.safetensors +3 -0
- model.safetensors-00005-of-00094.safetensors +3 -0
- model.safetensors-00006-of-00094.safetensors +3 -0
- model.safetensors-00007-of-00094.safetensors +3 -0
- model.safetensors-00008-of-00094.safetensors +3 -0
- model.safetensors-00009-of-00094.safetensors +3 -0
- model.safetensors-00010-of-00094.safetensors +3 -0
- model.safetensors-00011-of-00094.safetensors +3 -0
- model.safetensors-00012-of-00094.safetensors +3 -0
- model.safetensors-00013-of-00094.safetensors +3 -0
- model.safetensors-00014-of-00094.safetensors +3 -0
- model.safetensors-00015-of-00094.safetensors +3 -0
- model.safetensors-00016-of-00094.safetensors +3 -0
- model.safetensors-00017-of-00094.safetensors +3 -0
- model.safetensors-00018-of-00094.safetensors +3 -0
- model.safetensors-00019-of-00094.safetensors +3 -0
- model.safetensors-00020-of-00094.safetensors +3 -0
- model.safetensors-00021-of-00094.safetensors +3 -0
- model.safetensors-00022-of-00094.safetensors +3 -0
- model.safetensors-00023-of-00094.safetensors +3 -0
- model.safetensors-00024-of-00094.safetensors +3 -0
- model.safetensors-00025-of-00094.safetensors +3 -0
- model.safetensors-00026-of-00094.safetensors +3 -0
- model.safetensors-00027-of-00094.safetensors +3 -0
- model.safetensors-00028-of-00094.safetensors +3 -0
- model.safetensors-00029-of-00094.safetensors +3 -0
- model.safetensors-00030-of-00094.safetensors +3 -0
- model.safetensors-00031-of-00094.safetensors +3 -0
- model.safetensors-00032-of-00094.safetensors +3 -0
- model.safetensors-00033-of-00094.safetensors +3 -0
- model.safetensors-00034-of-00094.safetensors +3 -0
- model.safetensors-00035-of-00094.safetensors +3 -0
- model.safetensors-00036-of-00094.safetensors +3 -0
- model.safetensors-00037-of-00094.safetensors +3 -0
- model.safetensors-00038-of-00094.safetensors +3 -0
- model.safetensors-00039-of-00094.safetensors +3 -0
- model.safetensors-00040-of-00094.safetensors +3 -0
- model.safetensors-00041-of-00094.safetensors +3 -0
- model.safetensors-00042-of-00094.safetensors +3 -0
- model.safetensors-00043-of-00094.safetensors +3 -0
- model.safetensors-00044-of-00094.safetensors +3 -0
- model.safetensors-00045-of-00094.safetensors +3 -0
- model.safetensors-00046-of-00094.safetensors +3 -0
- model.safetensors-00047-of-00094.safetensors +3 -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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 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 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 248056,
|
| 7 |
+
"model_type": "qwen3_5_moe",
|
| 8 |
+
"text_config": {
|
| 9 |
+
"attention_bias": false,
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"attn_output_gate": true,
|
| 12 |
+
"bos_token_id": null,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 248044,
|
| 15 |
+
"full_attention_interval": 4,
|
| 16 |
+
"head_dim": 256,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 4096,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"linear_attention",
|
| 66 |
+
"linear_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"linear_attention",
|
| 70 |
+
"linear_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"linear_attention",
|
| 74 |
+
"linear_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"linear_attention",
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"full_attention"
|
| 81 |
+
],
|
| 82 |
+
"linear_conv_kernel_dim": 4,
|
| 83 |
+
"linear_key_head_dim": 128,
|
| 84 |
+
"linear_num_key_heads": 16,
|
| 85 |
+
"linear_num_value_heads": 64,
|
| 86 |
+
"linear_value_head_dim": 128,
|
| 87 |
+
"mamba_ssm_dtype": "float32",
|
| 88 |
+
"max_position_embeddings": 262144,
|
| 89 |
+
"mlp_only_layers": [],
|
| 90 |
+
"model_type": "qwen3_5_moe_text",
|
| 91 |
+
"moe_intermediate_size": 1024,
|
| 92 |
+
"mtp_num_hidden_layers": 1,
|
| 93 |
+
"mtp_use_dedicated_embeddings": false,
|
| 94 |
+
"num_attention_heads": 32,
|
| 95 |
+
"num_experts": 256,
|
| 96 |
+
"num_experts_per_tok": 10,
|
| 97 |
+
"num_hidden_layers": 60,
|
| 98 |
+
"num_key_value_heads": 2,
|
| 99 |
+
"output_router_logits": false,
|
| 100 |
+
"pad_token_id": null,
|
| 101 |
+
"partial_rotary_factor": 0.25,
|
| 102 |
+
"rms_norm_eps": 1e-06,
|
| 103 |
+
"rope_parameters": {
|
| 104 |
+
"mrope_interleaved": true,
|
| 105 |
+
"mrope_section": [
|
| 106 |
+
11,
|
| 107 |
+
11,
|
| 108 |
+
10
|
| 109 |
+
],
|
| 110 |
+
"partial_rotary_factor": 0.25,
|
| 111 |
+
"rope_theta": 10000000,
|
| 112 |
+
"rope_type": "default"
|
| 113 |
+
},
|
| 114 |
+
"router_aux_loss_coef": 0.001,
|
| 115 |
+
"shared_expert_intermediate_size": 1024,
|
| 116 |
+
"tie_word_embeddings": false,
|
| 117 |
+
"use_cache": true,
|
| 118 |
+
"vocab_size": 248320
|
| 119 |
+
},
|
| 120 |
+
"tie_word_embeddings": false,
|
| 121 |
+
"transformers_version": "5.2.0.dev0",
|
| 122 |
+
"video_token_id": 248057,
|
| 123 |
+
"vision_config": {
|
| 124 |
+
"deepstack_visual_indexes": [],
|
| 125 |
+
"depth": 27,
|
| 126 |
+
"dtype": "bfloat16",
|
| 127 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 128 |
+
"hidden_size": 1152,
|
| 129 |
+
"in_channels": 3,
|
| 130 |
+
"initializer_range": 0.02,
|
| 131 |
+
"intermediate_size": 4304,
|
| 132 |
+
"model_type": "qwen3_5_moe",
|
| 133 |
+
"num_heads": 16,
|
| 134 |
+
"num_position_embeddings": 2304,
|
| 135 |
+
"out_hidden_size": 4096,
|
| 136 |
+
"patch_size": 16,
|
| 137 |
+
"spatial_merge_size": 2,
|
| 138 |
+
"temporal_patch_size": 2
|
| 139 |
+
},
|
| 140 |
+
"vision_end_token_id": 248054,
|
| 141 |
+
"vision_start_token_id": 248053
|
| 142 |
+
}
|
model.safetensors-00001-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbbd168d27765b146ec30dbd0b114bc3ef98c644107d6324349197580c318446
|
| 3 |
+
size 4294967440
|
model.safetensors-00002-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:827461137abe5a041096dc41f25c970ad46a0566949f152982557ce31afd1e7a
|
| 3 |
+
size 4294967440
|
model.safetensors-00003-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4174224da0819d6ce3336d925fdbace6b0aaceb39217309bf3e342e28e33e7a
|
| 3 |
+
size 4294967440
|
model.safetensors-00004-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c28c48e8b58aad7f45a57c564bb40fc998472ca93d66ee49e30a3b64d2ef452
|
| 3 |
+
size 4294967440
|
model.safetensors-00005-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3acf70b69c4ed80c9c473b5c956c1c92d878a286c52e796c169b382bede301a9
|
| 3 |
+
size 4294967440
|
model.safetensors-00006-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bcadb721cabf76ac19f67fa6ebd68be48cd112a3410860c0e3d0f00ce679137
|
| 3 |
+
size 4294967440
|
model.safetensors-00007-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64223a1ad4f9a21421acc38f75407f16142b23538c38a791b74129fb015d1538
|
| 3 |
+
size 4294967440
|
model.safetensors-00008-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8afd343ec10e97fb72e7e35559365530eab6e10c62a28e3e6bb1e4d1edb625cb
|
| 3 |
+
size 4294967440
|
model.safetensors-00009-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cbf8096afb365f9e6be5dca3d4bb1cdf9da3ea100a1ecc7fd0a5bd888a5103a
|
| 3 |
+
size 4294967440
|
model.safetensors-00010-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a63ef71da09498e22a8c6d0cc4cb649c99292611f41d8e8a2d5ef28bf15654
|
| 3 |
+
size 4294967440
|
model.safetensors-00011-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ba26a492d7170aa90ff1bda1ebe12795261fbf249d035dc58f2ac67b5fd29e2
|
| 3 |
+
size 4294967440
|
model.safetensors-00012-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92ac7f01a057bdda3c60eba7dc191cdb645252f07117c83595acb7a1ff95c0ad
|
| 3 |
+
size 4294967440
|
model.safetensors-00013-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8d73cd7a63641a643e774f9f5ba8017b4bbd461db8102b3036d7a6430e597bf
|
| 3 |
+
size 4294967440
|
model.safetensors-00014-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:916715054be61a0ff7130b1cf986070d1ad0d4aac9192944da29a5fa6f47e0b1
|
| 3 |
+
size 4294967440
|
model.safetensors-00015-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:862156c3e36ffcf506949830b83172d50c22540fe3824462776212a17f6e8632
|
| 3 |
+
size 4294967440
|
model.safetensors-00016-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f158ffc3f43f5dd77372811ce354a787da3b2a012dd5a75420aa94ccad8c5eb
|
| 3 |
+
size 4294967440
|
model.safetensors-00017-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cc7eeb02da36b645e0a035c126e645b89fbc2d1983e45441f487770307a52a4
|
| 3 |
+
size 4294967440
|
model.safetensors-00018-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d297e990b8d8dd92173301e71a5af8bcb106bd0c2d9e7c82eb44ba8c9fe42e80
|
| 3 |
+
size 4294967440
|
model.safetensors-00019-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:212f8fa9ab07433ed5752669debe649c5353cbd26a063eaa8fb2248f5b3dd0f1
|
| 3 |
+
size 4294967440
|
model.safetensors-00020-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c69bf01679e9310bc81a7ac24c12ea2443534403b24726e11f98938bae339fa
|
| 3 |
+
size 4294967440
|
model.safetensors-00021-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:981d12a7ab2fe63c0382f9087099f3359c50216b89de81444ca877291bff3bc8
|
| 3 |
+
size 4294967440
|
model.safetensors-00022-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7077d0b2e6d877626fd4cc761b8f81f710ed62b03386b0f56169c8656dc3079
|
| 3 |
+
size 4294967440
|
model.safetensors-00023-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e31848adcfdf02c10c172c1aaa9211b636c7f15958844e31729c195aacf33669
|
| 3 |
+
size 4294967440
|
model.safetensors-00024-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02fd71b3fe9111bde7b10b21586ab231b5dda42f457e84886a4e1949e5c403f4
|
| 3 |
+
size 4294967440
|
model.safetensors-00025-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66fda1703475fda1f9b7a4ec6db969e23535a13b296a602eabedb908eccef30a
|
| 3 |
+
size 4294967440
|
model.safetensors-00026-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7dd8668b0d1830a90d50fc0fab841736535f90cb908927d58b49dfaa811865a
|
| 3 |
+
size 4294967440
|
model.safetensors-00027-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5643b262b823727a98fc0b35ca3fa3ea933a93a1ae83ddbfcc18d2ced8669173
|
| 3 |
+
size 4294967440
|
model.safetensors-00028-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fb7f44ea783d7da16a9fd9ae017dbf76a68973ad89ccda9c61acd5d61f82383
|
| 3 |
+
size 4294967440
|
model.safetensors-00029-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80fcfc0c964547401c64cfdf47b4b253bcaa295bcdbd283d9ba452be55f0745f
|
| 3 |
+
size 4294967440
|
model.safetensors-00030-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e96e2fa61e71150f95552bc20ed4d32b247ba87aa552b6e27e5f7edbd02dd5e5
|
| 3 |
+
size 4294967440
|
model.safetensors-00031-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad5ed439e100e48263470f82623971681c629c79facd543535be5a4ba17ceefe
|
| 3 |
+
size 4294967440
|
model.safetensors-00032-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f788a7802ca36e629b0326b42952776e1f1bc2a7a3ad4ba0caa90e41fd19ccaf
|
| 3 |
+
size 4294967440
|
model.safetensors-00033-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d87fd19d7277030549d7390c1c42bd7c79c1c6da6d554a1b12786d903276aa4
|
| 3 |
+
size 4294967440
|
model.safetensors-00034-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a78b76d179f4c0b8117058be010c0566019b23b225dd7c6d0cafd2520e9d1af6
|
| 3 |
+
size 4294967440
|
model.safetensors-00035-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1da9ce479fedd7f76ca7c70f7fbe4155b76db0dc91d5a65e58ac9c1d1893144e
|
| 3 |
+
size 4294967440
|
model.safetensors-00036-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1f7ea443d6b4ecfe22aae0418db7f1fa88d2f86fa263ae8165401b00dc4d27a
|
| 3 |
+
size 4294967440
|
model.safetensors-00037-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c50838b2e97963afb645f974f692801687cf3d685e55e2594cbc00ad1e53ee39
|
| 3 |
+
size 4294967440
|
model.safetensors-00038-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d331cb9141814117844aa322c1357c7a264d155bd885243c96f3c9ae563fe334
|
| 3 |
+
size 4294967440
|
model.safetensors-00039-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3971fc8b468fbd433812cd27a12a07e0d5b76c14b6e3ef8b5b9ee5fc40c31169
|
| 3 |
+
size 4294967440
|
model.safetensors-00040-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c0512010dc4e6b216a1093a461890cce4b622815d58c307d3d5c2a2f10e5130
|
| 3 |
+
size 4294967440
|
model.safetensors-00041-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e27c65748db8208945e474c4fc4d5d0e52c2c9c858fc070c2b5183ebbb3a2f2
|
| 3 |
+
size 4294967440
|
model.safetensors-00042-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01a02ff4d7312e874867aa32dd19b872aa29d797d54ff24989be2681cbb0722f
|
| 3 |
+
size 4294967440
|
model.safetensors-00043-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d553d73b44d9df0493fab553fb774e709c729413219c26782041bb5c14866186
|
| 3 |
+
size 4294967440
|
model.safetensors-00044-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9dffa5d5f4b6601d4fcf8be91168a157362e2bfd46346c558cd346daca502d
|
| 3 |
+
size 4294967440
|
model.safetensors-00045-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1e82e62127b75b1f10639a3978054eec74f6e9a064d934568bf8a623d630635
|
| 3 |
+
size 4294967440
|
model.safetensors-00046-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e80ba43e431e2342f16fb2b9157a85536cfc53d05a5d1cd091d33e45e7ed483
|
| 3 |
+
size 4294967440
|
model.safetensors-00047-of-00094.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:240640cc9937ab617a0de416ba2f50a9b338f4178a78afb9ba5056a97e9f9960
|
| 3 |
+
size 4294967440
|