Upload folder using huggingface_hub
Browse files- chat_template.json +3 -0
- config.json +318 -0
- generation_config.json +14 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +21 -0
- tokenizer.json +0 -0
- tokenizer_config.json +239 -0
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 151655,
|
| 6 |
+
"model_type": "qwen3_vl",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 151645,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 5120,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 25600,
|
| 18 |
+
"max_position_embeddings": 262144,
|
| 19 |
+
"model_type": "qwen3_vl_text",
|
| 20 |
+
"num_attention_heads": 64,
|
| 21 |
+
"num_hidden_layers": 64,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"mrope_interleaved": true,
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
24,
|
| 28 |
+
20,
|
| 29 |
+
20
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 5000000,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 151936
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"transformers_version": "4.57.0.dev0",
|
| 39 |
+
"video_token_id": 151656,
|
| 40 |
+
"vision_config": {
|
| 41 |
+
"deepstack_visual_indexes": [
|
| 42 |
+
8,
|
| 43 |
+
16,
|
| 44 |
+
24
|
| 45 |
+
],
|
| 46 |
+
"depth": 27,
|
| 47 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 48 |
+
"hidden_size": 1152,
|
| 49 |
+
"in_channels": 3,
|
| 50 |
+
"initializer_range": 0.02,
|
| 51 |
+
"intermediate_size": 4304,
|
| 52 |
+
"model_type": "qwen3_vl",
|
| 53 |
+
"num_heads": 16,
|
| 54 |
+
"num_position_embeddings": 2304,
|
| 55 |
+
"out_hidden_size": 5120,
|
| 56 |
+
"patch_size": 16,
|
| 57 |
+
"spatial_merge_size": 2,
|
| 58 |
+
"temporal_patch_size": 2
|
| 59 |
+
},
|
| 60 |
+
"vision_end_token_id": 151653,
|
| 61 |
+
"vision_start_token_id": 151652,
|
| 62 |
+
"quantization_config": {
|
| 63 |
+
"activation_scheme": "dynamic",
|
| 64 |
+
"fmt": "e4m3",
|
| 65 |
+
"quant_method": "fp8",
|
| 66 |
+
"ignored_layers": [
|
| 67 |
+
"lm_head",
|
| 68 |
+
"model.visual.merger.linear_fc1",
|
| 69 |
+
"model.visual.merger.linear_fc2",
|
| 70 |
+
"model.visual.merger.norm",
|
| 71 |
+
"model.visual.patch_embed.proj",
|
| 72 |
+
"model.visual.pos_embed",
|
| 73 |
+
"visual.merger.linear_fc1",
|
| 74 |
+
"visual.merger.linear_fc2",
|
| 75 |
+
"visual.merger.norm",
|
| 76 |
+
"visual.patch_embed.proj",
|
| 77 |
+
"visual.pos_embed",
|
| 78 |
+
"model.visual.blocks.0.attn.proj",
|
| 79 |
+
"model.visual.blocks.0.attn.qkv",
|
| 80 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 81 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 82 |
+
"visual.blocks.0.attn.proj",
|
| 83 |
+
"visual.blocks.0.attn.qkv_proj",
|
| 84 |
+
"visual.blocks.0.mlp.linear_fc1",
|
| 85 |
+
"visual.blocks.0.mlp.linear_fc2",
|
| 86 |
+
"model.visual.blocks.1.attn.proj",
|
| 87 |
+
"model.visual.blocks.1.attn.qkv",
|
| 88 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 89 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 90 |
+
"visual.blocks.1.attn.proj",
|
| 91 |
+
"visual.blocks.1.attn.qkv_proj",
|
| 92 |
+
"visual.blocks.1.mlp.linear_fc1",
|
| 93 |
+
"visual.blocks.1.mlp.linear_fc2",
|
| 94 |
+
"model.visual.blocks.2.attn.proj",
|
| 95 |
+
"model.visual.blocks.2.attn.qkv",
|
| 96 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 97 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 98 |
+
"visual.blocks.2.attn.proj",
|
| 99 |
+
"visual.blocks.2.attn.qkv_proj",
|
| 100 |
+
"visual.blocks.2.mlp.linear_fc1",
|
| 101 |
+
"visual.blocks.2.mlp.linear_fc2",
|
| 102 |
+
"model.visual.blocks.3.attn.proj",
|
| 103 |
+
"model.visual.blocks.3.attn.qkv",
|
| 104 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 105 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 106 |
+
"visual.blocks.3.attn.proj",
|
| 107 |
+
"visual.blocks.3.attn.qkv_proj",
|
| 108 |
+
"visual.blocks.3.mlp.linear_fc1",
|
| 109 |
+
"visual.blocks.3.mlp.linear_fc2",
|
| 110 |
+
"model.visual.blocks.4.attn.proj",
|
| 111 |
+
"model.visual.blocks.4.attn.qkv",
|
| 112 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 113 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 114 |
+
"visual.blocks.4.attn.proj",
|
| 115 |
+
"visual.blocks.4.attn.qkv_proj",
|
| 116 |
+
"visual.blocks.4.mlp.linear_fc1",
|
| 117 |
+
"visual.blocks.4.mlp.linear_fc2",
|
| 118 |
+
"model.visual.blocks.5.attn.proj",
|
| 119 |
+
"model.visual.blocks.5.attn.qkv",
|
| 120 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 121 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 122 |
+
"visual.blocks.5.attn.proj",
|
| 123 |
+
"visual.blocks.5.attn.qkv_proj",
|
| 124 |
+
"visual.blocks.5.mlp.linear_fc1",
|
| 125 |
+
"visual.blocks.5.mlp.linear_fc2",
|
| 126 |
+
"model.visual.blocks.6.attn.proj",
|
| 127 |
+
"model.visual.blocks.6.attn.qkv",
|
| 128 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 129 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 130 |
+
"visual.blocks.6.attn.proj",
|
| 131 |
+
"visual.blocks.6.attn.qkv_proj",
|
| 132 |
+
"visual.blocks.6.mlp.linear_fc1",
|
| 133 |
+
"visual.blocks.6.mlp.linear_fc2",
|
| 134 |
+
"model.visual.blocks.7.attn.proj",
|
| 135 |
+
"model.visual.blocks.7.attn.qkv",
|
| 136 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 137 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 138 |
+
"visual.blocks.7.attn.proj",
|
| 139 |
+
"visual.blocks.7.attn.qkv_proj",
|
| 140 |
+
"visual.blocks.7.mlp.linear_fc1",
|
| 141 |
+
"visual.blocks.7.mlp.linear_fc2",
|
| 142 |
+
"model.visual.blocks.8.attn.proj",
|
| 143 |
+
"model.visual.blocks.8.attn.qkv",
|
| 144 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 145 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 146 |
+
"visual.blocks.8.attn.proj",
|
| 147 |
+
"visual.blocks.8.attn.qkv_proj",
|
| 148 |
+
"visual.blocks.8.mlp.linear_fc1",
|
| 149 |
+
"visual.blocks.8.mlp.linear_fc2",
|
| 150 |
+
"model.visual.blocks.9.attn.proj",
|
| 151 |
+
"model.visual.blocks.9.attn.qkv",
|
| 152 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 153 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 154 |
+
"visual.blocks.9.attn.proj",
|
| 155 |
+
"visual.blocks.9.attn.qkv_proj",
|
| 156 |
+
"visual.blocks.9.mlp.linear_fc1",
|
| 157 |
+
"visual.blocks.9.mlp.linear_fc2",
|
| 158 |
+
"model.visual.blocks.10.attn.proj",
|
| 159 |
+
"model.visual.blocks.10.attn.qkv",
|
| 160 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 161 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 162 |
+
"visual.blocks.10.attn.proj",
|
| 163 |
+
"visual.blocks.10.attn.qkv_proj",
|
| 164 |
+
"visual.blocks.10.mlp.linear_fc1",
|
| 165 |
+
"visual.blocks.10.mlp.linear_fc2",
|
| 166 |
+
"model.visual.blocks.11.attn.proj",
|
| 167 |
+
"model.visual.blocks.11.attn.qkv",
|
| 168 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 169 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 170 |
+
"visual.blocks.11.attn.proj",
|
| 171 |
+
"visual.blocks.11.attn.qkv_proj",
|
| 172 |
+
"visual.blocks.11.mlp.linear_fc1",
|
| 173 |
+
"visual.blocks.11.mlp.linear_fc2",
|
| 174 |
+
"model.visual.blocks.12.attn.proj",
|
| 175 |
+
"model.visual.blocks.12.attn.qkv",
|
| 176 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 177 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 178 |
+
"visual.blocks.12.attn.proj",
|
| 179 |
+
"visual.blocks.12.attn.qkv_proj",
|
| 180 |
+
"visual.blocks.12.mlp.linear_fc1",
|
| 181 |
+
"visual.blocks.12.mlp.linear_fc2",
|
| 182 |
+
"model.visual.blocks.13.attn.proj",
|
| 183 |
+
"model.visual.blocks.13.attn.qkv",
|
| 184 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 185 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 186 |
+
"visual.blocks.13.attn.proj",
|
| 187 |
+
"visual.blocks.13.attn.qkv_proj",
|
| 188 |
+
"visual.blocks.13.mlp.linear_fc1",
|
| 189 |
+
"visual.blocks.13.mlp.linear_fc2",
|
| 190 |
+
"model.visual.blocks.14.attn.proj",
|
| 191 |
+
"model.visual.blocks.14.attn.qkv",
|
| 192 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 193 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 194 |
+
"visual.blocks.14.attn.proj",
|
| 195 |
+
"visual.blocks.14.attn.qkv_proj",
|
| 196 |
+
"visual.blocks.14.mlp.linear_fc1",
|
| 197 |
+
"visual.blocks.14.mlp.linear_fc2",
|
| 198 |
+
"model.visual.blocks.15.attn.proj",
|
| 199 |
+
"model.visual.blocks.15.attn.qkv",
|
| 200 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 201 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 202 |
+
"visual.blocks.15.attn.proj",
|
| 203 |
+
"visual.blocks.15.attn.qkv_proj",
|
| 204 |
+
"visual.blocks.15.mlp.linear_fc1",
|
| 205 |
+
"visual.blocks.15.mlp.linear_fc2",
|
| 206 |
+
"model.visual.blocks.16.attn.proj",
|
| 207 |
+
"model.visual.blocks.16.attn.qkv",
|
| 208 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 209 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 210 |
+
"visual.blocks.16.attn.proj",
|
| 211 |
+
"visual.blocks.16.attn.qkv_proj",
|
| 212 |
+
"visual.blocks.16.mlp.linear_fc1",
|
| 213 |
+
"visual.blocks.16.mlp.linear_fc2",
|
| 214 |
+
"model.visual.blocks.17.attn.proj",
|
| 215 |
+
"model.visual.blocks.17.attn.qkv",
|
| 216 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 217 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 218 |
+
"visual.blocks.17.attn.proj",
|
| 219 |
+
"visual.blocks.17.attn.qkv_proj",
|
| 220 |
+
"visual.blocks.17.mlp.linear_fc1",
|
| 221 |
+
"visual.blocks.17.mlp.linear_fc2",
|
| 222 |
+
"model.visual.blocks.18.attn.proj",
|
| 223 |
+
"model.visual.blocks.18.attn.qkv",
|
| 224 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 225 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 226 |
+
"visual.blocks.18.attn.proj",
|
| 227 |
+
"visual.blocks.18.attn.qkv_proj",
|
| 228 |
+
"visual.blocks.18.mlp.linear_fc1",
|
| 229 |
+
"visual.blocks.18.mlp.linear_fc2",
|
| 230 |
+
"model.visual.blocks.19.attn.proj",
|
| 231 |
+
"model.visual.blocks.19.attn.qkv",
|
| 232 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 233 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 234 |
+
"visual.blocks.19.attn.proj",
|
| 235 |
+
"visual.blocks.19.attn.qkv_proj",
|
| 236 |
+
"visual.blocks.19.mlp.linear_fc1",
|
| 237 |
+
"visual.blocks.19.mlp.linear_fc2",
|
| 238 |
+
"model.visual.blocks.20.attn.proj",
|
| 239 |
+
"model.visual.blocks.20.attn.qkv",
|
| 240 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 241 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 242 |
+
"visual.blocks.20.attn.proj",
|
| 243 |
+
"visual.blocks.20.attn.qkv_proj",
|
| 244 |
+
"visual.blocks.20.mlp.linear_fc1",
|
| 245 |
+
"visual.blocks.20.mlp.linear_fc2",
|
| 246 |
+
"model.visual.blocks.21.attn.proj",
|
| 247 |
+
"model.visual.blocks.21.attn.qkv",
|
| 248 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 249 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 250 |
+
"visual.blocks.21.attn.proj",
|
| 251 |
+
"visual.blocks.21.attn.qkv_proj",
|
| 252 |
+
"visual.blocks.21.mlp.linear_fc1",
|
| 253 |
+
"visual.blocks.21.mlp.linear_fc2",
|
| 254 |
+
"model.visual.blocks.22.attn.proj",
|
| 255 |
+
"model.visual.blocks.22.attn.qkv",
|
| 256 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 257 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 258 |
+
"visual.blocks.22.attn.proj",
|
| 259 |
+
"visual.blocks.22.attn.qkv_proj",
|
| 260 |
+
"visual.blocks.22.mlp.linear_fc1",
|
| 261 |
+
"visual.blocks.22.mlp.linear_fc2",
|
| 262 |
+
"model.visual.blocks.23.attn.proj",
|
| 263 |
+
"model.visual.blocks.23.attn.qkv",
|
| 264 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 265 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 266 |
+
"visual.blocks.23.attn.proj",
|
| 267 |
+
"visual.blocks.23.attn.qkv_proj",
|
| 268 |
+
"visual.blocks.23.mlp.linear_fc1",
|
| 269 |
+
"visual.blocks.23.mlp.linear_fc2",
|
| 270 |
+
"model.visual.blocks.24.attn.proj",
|
| 271 |
+
"model.visual.blocks.24.attn.qkv",
|
| 272 |
+
"model.visual.blocks.24.mlp.linear_fc1",
|
| 273 |
+
"model.visual.blocks.24.mlp.linear_fc2",
|
| 274 |
+
"visual.blocks.24.attn.proj",
|
| 275 |
+
"visual.blocks.24.attn.qkv_proj",
|
| 276 |
+
"visual.blocks.24.mlp.linear_fc1",
|
| 277 |
+
"visual.blocks.24.mlp.linear_fc2",
|
| 278 |
+
"model.visual.blocks.25.attn.proj",
|
| 279 |
+
"model.visual.blocks.25.attn.qkv",
|
| 280 |
+
"model.visual.blocks.25.mlp.linear_fc1",
|
| 281 |
+
"model.visual.blocks.25.mlp.linear_fc2",
|
| 282 |
+
"visual.blocks.25.attn.proj",
|
| 283 |
+
"visual.blocks.25.attn.qkv_proj",
|
| 284 |
+
"visual.blocks.25.mlp.linear_fc1",
|
| 285 |
+
"visual.blocks.25.mlp.linear_fc2",
|
| 286 |
+
"model.visual.blocks.26.attn.proj",
|
| 287 |
+
"model.visual.blocks.26.attn.qkv",
|
| 288 |
+
"model.visual.blocks.26.mlp.linear_fc1",
|
| 289 |
+
"model.visual.blocks.26.mlp.linear_fc2",
|
| 290 |
+
"visual.blocks.26.attn.proj",
|
| 291 |
+
"visual.blocks.26.attn.qkv_proj",
|
| 292 |
+
"visual.blocks.26.mlp.linear_fc1",
|
| 293 |
+
"visual.blocks.26.mlp.linear_fc2",
|
| 294 |
+
"model.visual.deepstack_merger_list.0.linear_fc1",
|
| 295 |
+
"model.visual.deepstack_merger_list.0.linear_fc2",
|
| 296 |
+
"model.visual.deepstack_merger_list.0.norm",
|
| 297 |
+
"visual.deepstack_merger_list.0.linear_fc1",
|
| 298 |
+
"visual.deepstack_merger_list.0.linear_fc2",
|
| 299 |
+
"visual.deepstack_merger_list.0.norm",
|
| 300 |
+
"model.visual.deepstack_merger_list.1.linear_fc1",
|
| 301 |
+
"model.visual.deepstack_merger_list.1.linear_fc2",
|
| 302 |
+
"model.visual.deepstack_merger_list.1.norm",
|
| 303 |
+
"visual.deepstack_merger_list.1.linear_fc1",
|
| 304 |
+
"visual.deepstack_merger_list.1.linear_fc2",
|
| 305 |
+
"visual.deepstack_merger_list.1.norm",
|
| 306 |
+
"model.visual.deepstack_merger_list.2.linear_fc1",
|
| 307 |
+
"model.visual.deepstack_merger_list.2.linear_fc2",
|
| 308 |
+
"model.visual.deepstack_merger_list.2.norm",
|
| 309 |
+
"visual.deepstack_merger_list.2.linear_fc1",
|
| 310 |
+
"visual.deepstack_merger_list.2.linear_fc2",
|
| 311 |
+
"visual.deepstack_merger_list.2.norm"
|
| 312 |
+
],
|
| 313 |
+
"weight_block_size": [
|
| 314 |
+
128,
|
| 315 |
+
128
|
| 316 |
+
]
|
| 317 |
+
}
|
| 318 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"repetition_penalty": 1.0,
|
| 12 |
+
"temperature": 0.8,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec789744e6eb67552e4f823677233740d1d8c066f1a020623a842191ae42f0e6
|
| 3 |
+
size 5324789312
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f68bc10a72221f49da85a15e31a4786c14c60dfc773436db7a284a1002c98ef3
|
| 3 |
+
size 5365032312
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04ebbb248f80779909d81641cf107106240d7e1ef0616710e7f8b8e9dc1aaa12
|
| 3 |
+
size 5365032312
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:813a2a4c8b785e6c5037c668acd0b9f36cc250b243132d2ecee47c2cd30e9285
|
| 3 |
+
size 5365032312
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ddf87034ce9a81f4ab81af45ac1d74005c09d3819c1a88bc02f49960b70eb77
|
| 3 |
+
size 5365032312
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:426b4ce0630a3bb91169a6ef9cfd13bdf28f2245c18a315d29d11c6f9eb21351
|
| 3 |
+
size 5365032312
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:403b509e3cb720ec7064bfd2a4a5ccd1c3ec4e1c8bd8f956587d02d97e2f31f2
|
| 3 |
+
size 3367015312
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
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
|
|
|