Hugging Face's logo

unsloth
/
Qwen3.6-35B-A3B-NVFP4-Fast

Image-Text-to-Text
Transformers
Safetensors
qwen3_5_moe
unsloth
qwen
qwen3_5
conversational
8-bit precision
compressed-tensors
Model card Files
xet
 Community
8
danielhanchen commited on
Commit
03104f1
·
verified ·
1 Parent(s): 8f072ad

Add files using upload-large-folder tool

Browse files
Files changed (17) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +154 -0
  3. config.json +535 -0
  4. configuration.json +1 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00005.safetensors +3 -0
  7. model-00002-of-00005.safetensors +3 -0
  8. model-00003-of-00005.safetensors +3 -0
  9. model-00004-of-00005.safetensors +3 -0
  10. model-00005-of-00005.safetensors +3 -0
  11. model.safetensors.index.json +3 -0
  12. preprocessor_config.json +21 -0
  13. processor_config.json +60 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +33 -0
  16. video_preprocessor_config.json +21 -0
  17. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ model.safetensors.index.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 +1,535 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "head_dim": 256,
7
+ "image_token_id": 248056,
8
+ "model_type": "qwen3_5_moe",
9
+ "num_attention_heads": 16,
10
+ "num_key_value_heads": 2,
11
+ "quantization_config": {
12
+ "config_groups": {
13
+ "group_0": {
14
+ "format": "float-quantized",
15
+ "input_activations": {
16
+ "actorder": null,
17
+ "block_structure": null,
18
+ "dynamic": true,
19
+ "group_size": null,
20
+ "num_bits": 8,
21
+ "observer": null,
22
+ "observer_kwargs": {},
23
+ "scale_dtype": null,
24
+ "strategy": "token",
25
+ "symmetric": true,
26
+ "type": "float",
27
+ "zp_dtype": null
28
+ },
29
+ "output_activations": null,
30
+ "targets": [
31
+ "re:.*self_attn\\.(q|k|v|o)_proj$",
32
+ "re:.*linear_attn\\.(in_proj_qkv|in_proj_z|out_proj)$",
33
+ "re:.*lm_head"
34
+ ],
35
+ "weights": {
36
+ "actorder": null,
37
+ "block_structure": null,
38
+ "dynamic": false,
39
+ "group_size": null,
40
+ "num_bits": 8,
41
+ "observer": "memoryless_minmax",
42
+ "observer_kwargs": {},
43
+ "scale_dtype": null,
44
+ "strategy": "channel",
45
+ "symmetric": true,
46
+ "type": "float",
47
+ "zp_dtype": null
48
+ }
49
+ },
50
+ "group_1": {
51
+ "format": "nvfp4-pack-quantized",
52
+ "input_activations": {
53
+ "actorder": null,
54
+ "block_structure": null,
55
+ "dynamic": "local",
56
+ "group_size": 16,
57
+ "num_bits": 4,
58
+ "observer": "static_minmax",
59
+ "observer_kwargs": {},
60
+ "scale_dtype": "torch.float8_e4m3fn",
61
+ "strategy": "tensor_group",
62
+ "symmetric": true,
63
+ "type": "float",
64
+ "zp_dtype": null
65
+ },
66
+ "output_activations": null,
67
+ "targets": [
68
+ "re:.*mlp\\.experts\\.\\d+\\.(gate|up|down)_proj$",
69
+ "re:.*shared_expert\\.(gate|up|down)_proj$"
70
+ ],
71
+ "weights": {
72
+ "actorder": null,
73
+ "block_structure": null,
74
+ "dynamic": false,
75
+ "group_size": 16,
76
+ "num_bits": 4,
77
+ "observer": "memoryless_minmax",
78
+ "observer_kwargs": {},
79
+ "scale_dtype": "torch.float8_e4m3fn",
80
+ "strategy": "tensor_group",
81
+ "symmetric": true,
82
+ "type": "float",
83
+ "zp_dtype": null
84
+ }
85
+ }
86
+ },
87
+ "format": "mixed-precision",
88
+ "global_compression_ratio": null,
89
+ "ignore": [
90
+ "model.visual.blocks.0.attn.qkv",
91
+ "model.visual.blocks.0.attn.proj",
92
+ "model.visual.blocks.0.mlp.linear_fc1",
93
+ "model.visual.blocks.0.mlp.linear_fc2",
94
+ "model.visual.blocks.1.attn.qkv",
95
+ "model.visual.blocks.1.attn.proj",
96
+ "model.visual.blocks.1.mlp.linear_fc1",
97
+ "model.visual.blocks.1.mlp.linear_fc2",
98
+ "model.visual.blocks.2.attn.qkv",
99
+ "model.visual.blocks.2.attn.proj",
100
+ "model.visual.blocks.2.mlp.linear_fc1",
101
+ "model.visual.blocks.2.mlp.linear_fc2",
102
+ "model.visual.blocks.3.attn.qkv",
103
+ "model.visual.blocks.3.attn.proj",
104
+ "model.visual.blocks.3.mlp.linear_fc1",
105
+ "model.visual.blocks.3.mlp.linear_fc2",
106
+ "model.visual.blocks.4.attn.qkv",
107
+ "model.visual.blocks.4.attn.proj",
108
+ "model.visual.blocks.4.mlp.linear_fc1",
109
+ "model.visual.blocks.4.mlp.linear_fc2",
110
+ "model.visual.blocks.5.attn.qkv",
111
+ "model.visual.blocks.5.attn.proj",
112
+ "model.visual.blocks.5.mlp.linear_fc1",
113
+ "model.visual.blocks.5.mlp.linear_fc2",
114
+ "model.visual.blocks.6.attn.qkv",
115
+ "model.visual.blocks.6.attn.proj",
116
+ "model.visual.blocks.6.mlp.linear_fc1",
117
+ "model.visual.blocks.6.mlp.linear_fc2",
118
+ "model.visual.blocks.7.attn.qkv",
119
+ "model.visual.blocks.7.attn.proj",
120
+ "model.visual.blocks.7.mlp.linear_fc1",
121
+ "model.visual.blocks.7.mlp.linear_fc2",
122
+ "model.visual.blocks.8.attn.qkv",
123
+ "model.visual.blocks.8.attn.proj",
124
+ "model.visual.blocks.8.mlp.linear_fc1",
125
+ "model.visual.blocks.8.mlp.linear_fc2",
126
+ "model.visual.blocks.9.attn.qkv",
127
+ "model.visual.blocks.9.attn.proj",
128
+ "model.visual.blocks.9.mlp.linear_fc1",
129
+ "model.visual.blocks.9.mlp.linear_fc2",
130
+ "model.visual.blocks.10.attn.qkv",
131
+ "model.visual.blocks.10.attn.proj",
132
+ "model.visual.blocks.10.mlp.linear_fc1",
133
+ "model.visual.blocks.10.mlp.linear_fc2",
134
+ "model.visual.blocks.11.attn.qkv",
135
+ "model.visual.blocks.11.attn.proj",
136
+ "model.visual.blocks.11.mlp.linear_fc1",
137
+ "model.visual.blocks.11.mlp.linear_fc2",
138
+ "model.visual.blocks.12.attn.qkv",
139
+ "model.visual.blocks.12.attn.proj",
140
+ "model.visual.blocks.12.mlp.linear_fc1",
141
+ "model.visual.blocks.12.mlp.linear_fc2",
142
+ "model.visual.blocks.13.attn.qkv",
143
+ "model.visual.blocks.13.attn.proj",
144
+ "model.visual.blocks.13.mlp.linear_fc1",
145
+ "model.visual.blocks.13.mlp.linear_fc2",
146
+ "model.visual.blocks.14.attn.qkv",
147
+ "model.visual.blocks.14.attn.proj",
148
+ "model.visual.blocks.14.mlp.linear_fc1",
149
+ "model.visual.blocks.14.mlp.linear_fc2",
150
+ "model.visual.blocks.15.attn.qkv",
151
+ "model.visual.blocks.15.attn.proj",
152
+ "model.visual.blocks.15.mlp.linear_fc1",
153
+ "model.visual.blocks.15.mlp.linear_fc2",
154
+ "model.visual.blocks.16.attn.qkv",
155
+ "model.visual.blocks.16.attn.proj",
156
+ "model.visual.blocks.16.mlp.linear_fc1",
157
+ "model.visual.blocks.16.mlp.linear_fc2",
158
+ "model.visual.blocks.17.attn.qkv",
159
+ "model.visual.blocks.17.attn.proj",
160
+ "model.visual.blocks.17.mlp.linear_fc1",
161
+ "model.visual.blocks.17.mlp.linear_fc2",
162
+ "model.visual.blocks.18.attn.qkv",
163
+ "model.visual.blocks.18.attn.proj",
164
+ "model.visual.blocks.18.mlp.linear_fc1",
165
+ "model.visual.blocks.18.mlp.linear_fc2",
166
+ "model.visual.blocks.19.attn.qkv",
167
+ "model.visual.blocks.19.attn.proj",
168
+ "model.visual.blocks.19.mlp.linear_fc1",
169
+ "model.visual.blocks.19.mlp.linear_fc2",
170
+ "model.visual.blocks.20.attn.qkv",
171
+ "model.visual.blocks.20.attn.proj",
172
+ "model.visual.blocks.20.mlp.linear_fc1",
173
+ "model.visual.blocks.20.mlp.linear_fc2",
174
+ "model.visual.blocks.21.attn.qkv",
175
+ "model.visual.blocks.21.attn.proj",
176
+ "model.visual.blocks.21.mlp.linear_fc1",
177
+ "model.visual.blocks.21.mlp.linear_fc2",
178
+ "model.visual.blocks.22.attn.qkv",
179
+ "model.visual.blocks.22.attn.proj",
180
+ "model.visual.blocks.22.mlp.linear_fc1",
181
+ "model.visual.blocks.22.mlp.linear_fc2",
182
+ "model.visual.blocks.23.attn.qkv",
183
+ "model.visual.blocks.23.attn.proj",
184
+ "model.visual.blocks.23.mlp.linear_fc1",
185
+ "model.visual.blocks.23.mlp.linear_fc2",
186
+ "model.visual.blocks.24.attn.qkv",
187
+ "model.visual.blocks.24.attn.proj",
188
+ "model.visual.blocks.24.mlp.linear_fc1",
189
+ "model.visual.blocks.24.mlp.linear_fc2",
190
+ "model.visual.blocks.25.attn.qkv",
191
+ "model.visual.blocks.25.attn.proj",
192
+ "model.visual.blocks.25.mlp.linear_fc1",
193
+ "model.visual.blocks.25.mlp.linear_fc2",
194
+ "model.visual.blocks.26.attn.qkv",
195
+ "model.visual.blocks.26.attn.proj",
196
+ "model.visual.blocks.26.mlp.linear_fc1",
197
+ "model.visual.blocks.26.mlp.linear_fc2",
198
+ "model.visual.merger.linear_fc1",
199
+ "model.visual.merger.linear_fc2",
200
+ "model.language_model.layers.0.linear_attn",
201
+ "model.language_model.layers.0.linear_attn.norm",
202
+ "model.language_model.layers.0.linear_attn.in_proj_b",
203
+ "model.language_model.layers.0.linear_attn.in_proj_a",
204
+ "model.language_model.layers.0.mlp.gate",
205
+ "model.language_model.layers.0.mlp.shared_expert_gate",
206
+ "model.language_model.layers.1.linear_attn",
207
+ "model.language_model.layers.1.linear_attn.norm",
208
+ "model.language_model.layers.1.linear_attn.in_proj_b",
209
+ "model.language_model.layers.1.linear_attn.in_proj_a",
210
+ "model.language_model.layers.1.mlp.gate",
211
+ "model.language_model.layers.1.mlp.shared_expert_gate",
212
+ "model.language_model.layers.2.linear_attn",
213
+ "model.language_model.layers.2.linear_attn.norm",
214
+ "model.language_model.layers.2.linear_attn.in_proj_b",
215
+ "model.language_model.layers.2.linear_attn.in_proj_a",
216
+ "model.language_model.layers.2.mlp.gate",
217
+ "model.language_model.layers.2.mlp.shared_expert_gate",
218
+ "model.language_model.layers.3.mlp.gate",
219
+ "model.language_model.layers.3.mlp.shared_expert_gate",
220
+ "model.language_model.layers.4.linear_attn",
221
+ "model.language_model.layers.4.linear_attn.norm",
222
+ "model.language_model.layers.4.linear_attn.in_proj_b",
223
+ "model.language_model.layers.4.linear_attn.in_proj_a",
224
+ "model.language_model.layers.4.mlp.gate",
225
+ "model.language_model.layers.4.mlp.shared_expert_gate",
226
+ "model.language_model.layers.5.linear_attn",
227
+ "model.language_model.layers.5.linear_attn.norm",
228
+ "model.language_model.layers.5.linear_attn.in_proj_b",
229
+ "model.language_model.layers.5.linear_attn.in_proj_a",
230
+ "model.language_model.layers.5.mlp.gate",
231
+ "model.language_model.layers.5.mlp.shared_expert_gate",
232
+ "model.language_model.layers.6.linear_attn",
233
+ "model.language_model.layers.6.linear_attn.norm",
234
+ "model.language_model.layers.6.linear_attn.in_proj_b",
235
+ "model.language_model.layers.6.linear_attn.in_proj_a",
236
+ "model.language_model.layers.6.mlp.gate",
237
+ "model.language_model.layers.6.mlp.shared_expert_gate",
238
+ "model.language_model.layers.7.mlp.gate",
239
+ "model.language_model.layers.7.mlp.shared_expert_gate",
240
+ "model.language_model.layers.8.linear_attn",
241
+ "model.language_model.layers.8.linear_attn.norm",
242
+ "model.language_model.layers.8.linear_attn.in_proj_b",
243
+ "model.language_model.layers.8.linear_attn.in_proj_a",
244
+ "model.language_model.layers.8.mlp.gate",
245
+ "model.language_model.layers.8.mlp.shared_expert_gate",
246
+ "model.language_model.layers.9.linear_attn",
247
+ "model.language_model.layers.9.linear_attn.norm",
248
+ "model.language_model.layers.9.linear_attn.in_proj_b",
249
+ "model.language_model.layers.9.linear_attn.in_proj_a",
250
+ "model.language_model.layers.9.mlp.gate",
251
+ "model.language_model.layers.9.mlp.shared_expert_gate",
252
+ "model.language_model.layers.10.linear_attn",
253
+ "model.language_model.layers.10.linear_attn.norm",
254
+ "model.language_model.layers.10.linear_attn.in_proj_b",
255
+ "model.language_model.layers.10.linear_attn.in_proj_a",
256
+ "model.language_model.layers.10.mlp.gate",
257
+ "model.language_model.layers.10.mlp.shared_expert_gate",
258
+ "model.language_model.layers.11.mlp.gate",
259
+ "model.language_model.layers.11.mlp.shared_expert_gate",
260
+ "model.language_model.layers.12.linear_attn",
261
+ "model.language_model.layers.12.linear_attn.norm",
262
+ "model.language_model.layers.12.linear_attn.in_proj_b",
263
+ "model.language_model.layers.12.linear_attn.in_proj_a",
264
+ "model.language_model.layers.12.mlp.gate",
265
+ "model.language_model.layers.12.mlp.shared_expert_gate",
266
+ "model.language_model.layers.13.linear_attn",
267
+ "model.language_model.layers.13.linear_attn.norm",
268
+ "model.language_model.layers.13.linear_attn.in_proj_b",
269
+ "model.language_model.layers.13.linear_attn.in_proj_a",
270
+ "model.language_model.layers.13.mlp.gate",
271
+ "model.language_model.layers.13.mlp.shared_expert_gate",
272
+ "model.language_model.layers.14.linear_attn",
273
+ "model.language_model.layers.14.linear_attn.norm",
274
+ "model.language_model.layers.14.linear_attn.in_proj_b",
275
+ "model.language_model.layers.14.linear_attn.in_proj_a",
276
+ "model.language_model.layers.14.mlp.gate",
277
+ "model.language_model.layers.14.mlp.shared_expert_gate",
278
+ "model.language_model.layers.15.mlp.gate",
279
+ "model.language_model.layers.15.mlp.shared_expert_gate",
280
+ "model.language_model.layers.16.linear_attn",
281
+ "model.language_model.layers.16.linear_attn.norm",
282
+ "model.language_model.layers.16.linear_attn.in_proj_b",
283
+ "model.language_model.layers.16.linear_attn.in_proj_a",
284
+ "model.language_model.layers.16.mlp.gate",
285
+ "model.language_model.layers.16.mlp.shared_expert_gate",
286
+ "model.language_model.layers.17.linear_attn",
287
+ "model.language_model.layers.17.linear_attn.norm",
288
+ "model.language_model.layers.17.linear_attn.in_proj_b",
289
+ "model.language_model.layers.17.linear_attn.in_proj_a",
290
+ "model.language_model.layers.17.mlp.gate",
291
+ "model.language_model.layers.17.mlp.shared_expert_gate",
292
+ "model.language_model.layers.18.linear_attn",
293
+ "model.language_model.layers.18.linear_attn.norm",
294
+ "model.language_model.layers.18.linear_attn.in_proj_b",
295
+ "model.language_model.layers.18.linear_attn.in_proj_a",
296
+ "model.language_model.layers.18.mlp.gate",
297
+ "model.language_model.layers.18.mlp.shared_expert_gate",
298
+ "model.language_model.layers.19.mlp.gate",
299
+ "model.language_model.layers.19.mlp.shared_expert_gate",
300
+ "model.language_model.layers.20.linear_attn",
301
+ "model.language_model.layers.20.linear_attn.norm",
302
+ "model.language_model.layers.20.linear_attn.in_proj_b",
303
+ "model.language_model.layers.20.linear_attn.in_proj_a",
304
+ "model.language_model.layers.20.mlp.gate",
305
+ "model.language_model.layers.20.mlp.shared_expert_gate",
306
+ "model.language_model.layers.21.linear_attn",
307
+ "model.language_model.layers.21.linear_attn.norm",
308
+ "model.language_model.layers.21.linear_attn.in_proj_b",
309
+ "model.language_model.layers.21.linear_attn.in_proj_a",
310
+ "model.language_model.layers.21.mlp.gate",
311
+ "model.language_model.layers.21.mlp.shared_expert_gate",
312
+ "model.language_model.layers.22.linear_attn",
313
+ "model.language_model.layers.22.linear_attn.norm",
314
+ "model.language_model.layers.22.linear_attn.in_proj_b",
315
+ "model.language_model.layers.22.linear_attn.in_proj_a",
316
+ "model.language_model.layers.22.mlp.gate",
317
+ "model.language_model.layers.22.mlp.shared_expert_gate",
318
+ "model.language_model.layers.23.mlp.gate",
319
+ "model.language_model.layers.23.mlp.shared_expert_gate",
320
+ "model.language_model.layers.24.linear_attn",
321
+ "model.language_model.layers.24.linear_attn.norm",
322
+ "model.language_model.layers.24.linear_attn.in_proj_b",
323
+ "model.language_model.layers.24.linear_attn.in_proj_a",
324
+ "model.language_model.layers.24.mlp.gate",
325
+ "model.language_model.layers.24.mlp.shared_expert_gate",
326
+ "model.language_model.layers.25.linear_attn",
327
+ "model.language_model.layers.25.linear_attn.norm",
328
+ "model.language_model.layers.25.linear_attn.in_proj_b",
329
+ "model.language_model.layers.25.linear_attn.in_proj_a",
330
+ "model.language_model.layers.25.mlp.gate",
331
+ "model.language_model.layers.25.mlp.shared_expert_gate",
332
+ "model.language_model.layers.26.linear_attn",
333
+ "model.language_model.layers.26.linear_attn.norm",
334
+ "model.language_model.layers.26.linear_attn.in_proj_b",
335
+ "model.language_model.layers.26.linear_attn.in_proj_a",
336
+ "model.language_model.layers.26.mlp.gate",
337
+ "model.language_model.layers.26.mlp.shared_expert_gate",
338
+ "model.language_model.layers.27.mlp.gate",
339
+ "model.language_model.layers.27.mlp.shared_expert_gate",
340
+ "model.language_model.layers.28.linear_attn",
341
+ "model.language_model.layers.28.linear_attn.norm",
342
+ "model.language_model.layers.28.linear_attn.in_proj_b",
343
+ "model.language_model.layers.28.linear_attn.in_proj_a",
344
+ "model.language_model.layers.28.mlp.gate",
345
+ "model.language_model.layers.28.mlp.shared_expert_gate",
346
+ "model.language_model.layers.29.linear_attn",
347
+ "model.language_model.layers.29.linear_attn.norm",
348
+ "model.language_model.layers.29.linear_attn.in_proj_b",
349
+ "model.language_model.layers.29.linear_attn.in_proj_a",
350
+ "model.language_model.layers.29.mlp.gate",
351
+ "model.language_model.layers.29.mlp.shared_expert_gate",
352
+ "model.language_model.layers.30.linear_attn",
353
+ "model.language_model.layers.30.linear_attn.norm",
354
+ "model.language_model.layers.30.linear_attn.in_proj_b",
355
+ "model.language_model.layers.30.linear_attn.in_proj_a",
356
+ "model.language_model.layers.30.mlp.gate",
357
+ "model.language_model.layers.30.mlp.shared_expert_gate",
358
+ "model.language_model.layers.31.mlp.gate",
359
+ "model.language_model.layers.31.mlp.shared_expert_gate",
360
+ "model.language_model.layers.32.linear_attn",
361
+ "model.language_model.layers.32.linear_attn.norm",
362
+ "model.language_model.layers.32.linear_attn.in_proj_b",
363
+ "model.language_model.layers.32.linear_attn.in_proj_a",
364
+ "model.language_model.layers.32.mlp.gate",
365
+ "model.language_model.layers.32.mlp.shared_expert_gate",
366
+ "model.language_model.layers.33.linear_attn",
367
+ "model.language_model.layers.33.linear_attn.norm",
368
+ "model.language_model.layers.33.linear_attn.in_proj_b",
369
+ "model.language_model.layers.33.linear_attn.in_proj_a",
370
+ "model.language_model.layers.33.mlp.gate",
371
+ "model.language_model.layers.33.mlp.shared_expert_gate",
372
+ "model.language_model.layers.34.linear_attn",
373
+ "model.language_model.layers.34.linear_attn.norm",
374
+ "model.language_model.layers.34.linear_attn.in_proj_b",
375
+ "model.language_model.layers.34.linear_attn.in_proj_a",
376
+ "model.language_model.layers.34.mlp.gate",
377
+ "model.language_model.layers.34.mlp.shared_expert_gate",
378
+ "model.language_model.layers.35.mlp.gate",
379
+ "model.language_model.layers.35.mlp.shared_expert_gate",
380
+ "model.language_model.layers.36.linear_attn",
381
+ "model.language_model.layers.36.linear_attn.norm",
382
+ "model.language_model.layers.36.linear_attn.in_proj_b",
383
+ "model.language_model.layers.36.linear_attn.in_proj_a",
384
+ "model.language_model.layers.36.mlp.gate",
385
+ "model.language_model.layers.36.mlp.shared_expert_gate",
386
+ "model.language_model.layers.37.linear_attn",
387
+ "model.language_model.layers.37.linear_attn.norm",
388
+ "model.language_model.layers.37.linear_attn.in_proj_b",
389
+ "model.language_model.layers.37.linear_attn.in_proj_a",
390
+ "model.language_model.layers.37.mlp.gate",
391
+ "model.language_model.layers.37.mlp.shared_expert_gate",
392
+ "model.language_model.layers.38.linear_attn",
393
+ "model.language_model.layers.38.linear_attn.norm",
394
+ "model.language_model.layers.38.linear_attn.in_proj_b",
395
+ "model.language_model.layers.38.linear_attn.in_proj_a",
396
+ "model.language_model.layers.38.mlp.gate",
397
+ "model.language_model.layers.38.mlp.shared_expert_gate",
398
+ "model.language_model.layers.39.mlp.gate",
399
+ "model.language_model.layers.39.mlp.shared_expert_gate",
400
+ "re:^mtp.*"
401
+ ],
402
+ "kv_cache_scheme": {
403
+ "actorder": null,
404
+ "block_structure": null,
405
+ "dynamic": false,
406
+ "group_size": null,
407
+ "num_bits": 8,
408
+ "observer": "static_minmax",
409
+ "observer_kwargs": {},
410
+ "scale_dtype": null,
411
+ "strategy": "tensor",
412
+ "symmetric": true,
413
+ "type": "float",
414
+ "zp_dtype": null
415
+ },
416
+ "quant_method": "compressed-tensors",
417
+ "quantization_status": "compressed",
418
+ "sparsity_config": {},
419
+ "transform_config": {},
420
+ "version": "0.17.2.a20260707"
421
+ },
422
+ "text_config": {
423
+ "attention_bias": false,
424
+ "attention_dropout": 0.0,
425
+ "attn_output_gate": true,
426
+ "bos_token_id": 248044,
427
+ "dtype": "bfloat16",
428
+ "eos_token_id": 248044,
429
+ "full_attention_interval": 4,
430
+ "head_dim": 256,
431
+ "hidden_act": "silu",
432
+ "hidden_size": 2048,
433
+ "initializer_range": 0.02,
434
+ "layer_types": [
435
+ "linear_attention",
436
+ "linear_attention",
437
+ "linear_attention",
438
+ "full_attention",
439
+ "linear_attention",
440
+ "linear_attention",
441
+ "linear_attention",
442
+ "full_attention",
443
+ "linear_attention",
444
+ "linear_attention",
445
+ "linear_attention",
446
+ "full_attention",
447
+ "linear_attention",
448
+ "linear_attention",
449
+ "linear_attention",
450
+ "full_attention",
451
+ "linear_attention",
452
+ "linear_attention",
453
+ "linear_attention",
454
+ "full_attention",
455
+ "linear_attention",
456
+ "linear_attention",
457
+ "linear_attention",
458
+ "full_attention",
459
+ "linear_attention",
460
+ "linear_attention",
461
+ "linear_attention",
462
+ "full_attention",
463
+ "linear_attention",
464
+ "linear_attention",
465
+ "linear_attention",
466
+ "full_attention",
467
+ "linear_attention",
468
+ "linear_attention",
469
+ "linear_attention",
470
+ "full_attention",
471
+ "linear_attention",
472
+ "linear_attention",
473
+ "linear_attention",
474
+ "full_attention"
475
+ ],
476
+ "linear_conv_kernel_dim": 4,
477
+ "linear_key_head_dim": 128,
478
+ "linear_num_key_heads": 16,
479
+ "linear_num_value_heads": 32,
480
+ "linear_value_head_dim": 128,
481
+ "mamba_ssm_dtype": "float32",
482
+ "max_position_embeddings": 262144,
483
+ "model_type": "qwen3_5_moe_text",
484
+ "moe_intermediate_size": 512,
485
+ "mtp_num_hidden_layers": 1,
486
+ "mtp_use_dedicated_embeddings": false,
487
+ "num_attention_heads": 16,
488
+ "num_experts": 256,
489
+ "num_experts_per_tok": 8,
490
+ "num_hidden_layers": 40,
491
+ "num_key_value_heads": 2,
492
+ "output_router_logits": false,
493
+ "pad_token_id": null,
494
+ "partial_rotary_factor": 0.25,
495
+ "rms_norm_eps": 1e-06,
496
+ "rope_parameters": {
497
+ "mrope_interleaved": true,
498
+ "mrope_section": [
499
+ 11,
500
+ 11,
501
+ 10
502
+ ],
503
+ "partial_rotary_factor": 0.25,
504
+ "rope_theta": 10000000,
505
+ "rope_type": "default"
506
+ },
507
+ "router_aux_loss_coef": 0.001,
508
+ "shared_expert_intermediate_size": 512,
509
+ "tie_word_embeddings": false,
510
+ "use_cache": true,
511
+ "vocab_size": 248320
512
+ },
513
+ "tie_word_embeddings": false,
514
+ "transformers_version": "5.13.0",
515
+ "video_token_id": 248057,
516
+ "vision_config": {
517
+ "deepstack_visual_indexes": [],
518
+ "depth": 27,
519
+ "dtype": "bfloat16",
520
+ "hidden_act": "gelu_pytorch_tanh",
521
+ "hidden_size": 1152,
522
+ "in_channels": 3,
523
+ "initializer_range": 0.02,
524
+ "intermediate_size": 4304,
525
+ "model_type": "qwen3_5_moe_vision",
526
+ "num_heads": 16,
527
+ "num_position_embeddings": 2304,
528
+ "out_hidden_size": 2048,
529
+ "patch_size": 16,
530
+ "spatial_merge_size": 2,
531
+ "temporal_patch_size": 2
532
+ },
533
+ "vision_end_token_id": 248054,
534
+ "vision_start_token_id": 248053
535
+ }
configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework":"Pytorch","task":"visual-question-answering"}
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "transformers_version": "5.13.0"
13
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6d6df8a4bac85af79c6912b7360533107a8de89f8eb106008c872203f477b1
3
+ size 5002671628
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071ab0aa7b8e0ecf80227c6be51bfadb666d2b0566090ab261a439cbd765cb63
3
+ size 5004247852
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81191b3fe3fc8471cfa8be2014584864fbb03248aa1924823d1553b54243590
3
+ size 5003987116
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcc959e513844a39a53361f539e0588a03473889e39683a4ce32791f2e84c22
3
+ size 5004437760
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c56b1762626d3a2b7c53eddd4e3ae32c2574e79424c6d658de7f4f6405da29
3
+ size 3633643668
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ab515cf0dcc4fae3daf192b9c6af1d3a9b0e79a4e699892bc18a3013315fd7
3
+ size 14300018
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 sha256:1a6329cee073f44581f13a111a96addf12a9d9a65b2ac6f81fa441ec1b63f5c9
3
+ size 19989425
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