Hugging Face's logo

Intel
/
Qwen3-VL-30B-A3B-Instruct-int4-AutoRound

Safetensors
qwen3_vl_moe
4-bit precision
auto-round
Model card Files
xet
 Community
2
weiweiz1 commited on
Commit
d72c91d
·
verified ·
1 Parent(s): a33979a

Add files using upload-large-folder tool

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +120 -0
  4. config.json +466 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00004.safetensors +3 -0
  8. model-00002-of-00004.safetensors +3 -0
  9. model-00003-of-00004.safetensors +3 -0
  10. model-00004-of-00004.safetensors +3 -0
  11. model.safetensors.index.json +0 -0
  12. preprocessor_config.json +39 -0
  13. quantization_config.json +396 -0
  14. special_tokens_map.json +31 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +240 -0
  17. video_preprocessor_config.json +41 -0
  18. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if 'text' in content %}
9
+ {{- content.text }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- endif %}
13
+ {{- '\n\n' }}
14
+ {%- endif %}
15
+ {{- "# 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>" }}
16
+ {%- for tool in tools %}
17
+ {{- "\n" }}
18
+ {{- tool | tojson }}
19
+ {%- endfor %}
20
+ {{- "\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" }}
21
+ {%- else %}
22
+ {%- if messages[0].role == 'system' %}
23
+ {{- '<|im_start|>system\n' }}
24
+ {%- if messages[0].content is string %}
25
+ {{- messages[0].content }}
26
+ {%- else %}
27
+ {%- for content in messages[0].content %}
28
+ {%- if 'text' in content %}
29
+ {{- content.text }}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {%- endif %}
33
+ {{- '<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set image_count = namespace(value=0) %}
37
+ {%- set video_count = namespace(value=0) %}
38
+ {%- for message in messages %}
39
+ {%- if message.role == "user" %}
40
+ {{- '<|im_start|>' + message.role + '\n' }}
41
+ {%- if message.content is string %}
42
+ {{- message.content }}
43
+ {%- else %}
44
+ {%- for content in message.content %}
45
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
+ {%- set image_count.value = image_count.value + 1 %}
47
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
+ <|vision_start|><|image_pad|><|vision_end|>
49
+ {%- elif content.type == 'video' or 'video' in content %}
50
+ {%- set video_count.value = video_count.value + 1 %}
51
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
+ <|vision_start|><|video_pad|><|vision_end|>
53
+ {%- elif 'text' in content %}
54
+ {{- content.text }}
55
+ {%- endif %}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- elif message.role == "assistant" %}
60
+ {{- '<|im_start|>' + message.role + '\n' }}
61
+ {%- if message.content is string %}
62
+ {{- message.content }}
63
+ {%- else %}
64
+ {%- for content_item in message.content %}
65
+ {%- if 'text' in content_item %}
66
+ {{- content_item.text }}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+ {%- endif %}
70
+ {%- if message.tool_calls %}
71
+ {%- for tool_call in message.tool_calls %}
72
+ {%- if (loop.first and message.content) or (not loop.first) %}
73
+ {{- '\n' }}
74
+ {%- endif %}
75
+ {%- if tool_call.function %}
76
+ {%- set tool_call = tool_call.function %}
77
+ {%- endif %}
78
+ {{- '<tool_call>\n{"name": "' }}
79
+ {{- tool_call.name }}
80
+ {{- '", "arguments": ' }}
81
+ {%- if tool_call.arguments is string %}
82
+ {{- tool_call.arguments }}
83
+ {%- else %}
84
+ {{- tool_call.arguments | tojson }}
85
+ {%- endif %}
86
+ {{- '}\n</tool_call>' }}
87
+ {%- endfor %}
88
+ {%- endif %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- elif message.role == "tool" %}
91
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
+ {{- '<|im_start|>user' }}
93
+ {%- endif %}
94
+ {{- '\n<tool_response>\n' }}
95
+ {%- if message.content is string %}
96
+ {{- message.content }}
97
+ {%- else %}
98
+ {%- for content in message.content %}
99
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
+ {%- set image_count.value = image_count.value + 1 %}
101
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
+ <|vision_start|><|image_pad|><|vision_end|>
103
+ {%- elif content.type == 'video' or 'video' in content %}
104
+ {%- set video_count.value = video_count.value + 1 %}
105
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
+ <|vision_start|><|video_pad|><|vision_end|>
107
+ {%- elif 'text' in content %}
108
+ {{- content.text }}
109
+ {%- endif %}
110
+ {%- endfor %}
111
+ {%- endif %}
112
+ {{- '\n</tool_response>' }}
113
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
+ {{- '<|im_end|>\n' }}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if add_generation_prompt %}
119
+ {{- '<|im_start|>assistant\n' }}
120
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,466 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLMoeForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen3_vl_moe",
8
+ "quantization_config": {
9
+ "autoround_version": "0.9.5",
10
+ "bits": 4,
11
+ "block_name_to_quantize": "model.language_model.layers",
12
+ "data_type": "int",
13
+ "extra_config": {
14
+ "model.language_model.layers.0.mlp.gate": {
15
+ "act_bits": 16,
16
+ "act_data_type": "float",
17
+ "bits": 16,
18
+ "data_type": "float",
19
+ "group_size": 128,
20
+ "sym": true
21
+ },
22
+ "model.language_model.layers.1.mlp.gate": {
23
+ "act_bits": 16,
24
+ "act_data_type": "float",
25
+ "bits": 16,
26
+ "data_type": "float",
27
+ "group_size": 128,
28
+ "sym": true
29
+ },
30
+ "model.language_model.layers.10.mlp.gate": {
31
+ "act_bits": 16,
32
+ "act_data_type": "float",
33
+ "bits": 16,
34
+ "data_type": "float",
35
+ "group_size": 128,
36
+ "sym": true
37
+ },
38
+ "model.language_model.layers.11.mlp.gate": {
39
+ "act_bits": 16,
40
+ "act_data_type": "float",
41
+ "bits": 16,
42
+ "data_type": "float",
43
+ "group_size": 128,
44
+ "sym": true
45
+ },
46
+ "model.language_model.layers.12.mlp.gate": {
47
+ "act_bits": 16,
48
+ "act_data_type": "float",
49
+ "bits": 16,
50
+ "data_type": "float",
51
+ "group_size": 128,
52
+ "sym": true
53
+ },
54
+ "model.language_model.layers.13.mlp.gate": {
55
+ "act_bits": 16,
56
+ "act_data_type": "float",
57
+ "bits": 16,
58
+ "data_type": "float",
59
+ "group_size": 128,
60
+ "sym": true
61
+ },
62
+ "model.language_model.layers.14.mlp.gate": {
63
+ "act_bits": 16,
64
+ "act_data_type": "float",
65
+ "bits": 16,
66
+ "data_type": "float",
67
+ "group_size": 128,
68
+ "sym": true
69
+ },
70
+ "model.language_model.layers.15.mlp.gate": {
71
+ "act_bits": 16,
72
+ "act_data_type": "float",
73
+ "bits": 16,
74
+ "data_type": "float",
75
+ "group_size": 128,
76
+ "sym": true
77
+ },
78
+ "model.language_model.layers.16.mlp.gate": {
79
+ "act_bits": 16,
80
+ "act_data_type": "float",
81
+ "bits": 16,
82
+ "data_type": "float",
83
+ "group_size": 128,
84
+ "sym": true
85
+ },
86
+ "model.language_model.layers.17.mlp.gate": {
87
+ "act_bits": 16,
88
+ "act_data_type": "float",
89
+ "bits": 16,
90
+ "data_type": "float",
91
+ "group_size": 128,
92
+ "sym": true
93
+ },
94
+ "model.language_model.layers.18.mlp.gate": {
95
+ "act_bits": 16,
96
+ "act_data_type": "float",
97
+ "bits": 16,
98
+ "data_type": "float",
99
+ "group_size": 128,
100
+ "sym": true
101
+ },
102
+ "model.language_model.layers.19.mlp.gate": {
103
+ "act_bits": 16,
104
+ "act_data_type": "float",
105
+ "bits": 16,
106
+ "data_type": "float",
107
+ "group_size": 128,
108
+ "sym": true
109
+ },
110
+ "model.language_model.layers.2.mlp.gate": {
111
+ "act_bits": 16,
112
+ "act_data_type": "float",
113
+ "bits": 16,
114
+ "data_type": "float",
115
+ "group_size": 128,
116
+ "sym": true
117
+ },
118
+ "model.language_model.layers.20.mlp.gate": {
119
+ "act_bits": 16,
120
+ "act_data_type": "float",
121
+ "bits": 16,
122
+ "data_type": "float",
123
+ "group_size": 128,
124
+ "sym": true
125
+ },
126
+ "model.language_model.layers.21.mlp.gate": {
127
+ "act_bits": 16,
128
+ "act_data_type": "float",
129
+ "bits": 16,
130
+ "data_type": "float",
131
+ "group_size": 128,
132
+ "sym": true
133
+ },
134
+ "model.language_model.layers.22.mlp.gate": {
135
+ "act_bits": 16,
136
+ "act_data_type": "float",
137
+ "bits": 16,
138
+ "data_type": "float",
139
+ "group_size": 128,
140
+ "sym": true
141
+ },
142
+ "model.language_model.layers.23.mlp.gate": {
143
+ "act_bits": 16,
144
+ "act_data_type": "float",
145
+ "bits": 16,
146
+ "data_type": "float",
147
+ "group_size": 128,
148
+ "sym": true
149
+ },
150
+ "model.language_model.layers.24.mlp.gate": {
151
+ "act_bits": 16,
152
+ "act_data_type": "float",
153
+ "bits": 16,
154
+ "data_type": "float",
155
+ "group_size": 128,
156
+ "sym": true
157
+ },
158
+ "model.language_model.layers.25.mlp.gate": {
159
+ "act_bits": 16,
160
+ "act_data_type": "float",
161
+ "bits": 16,
162
+ "data_type": "float",
163
+ "group_size": 128,
164
+ "sym": true
165
+ },
166
+ "model.language_model.layers.26.mlp.gate": {
167
+ "act_bits": 16,
168
+ "act_data_type": "float",
169
+ "bits": 16,
170
+ "data_type": "float",
171
+ "group_size": 128,
172
+ "sym": true
173
+ },
174
+ "model.language_model.layers.27.mlp.gate": {
175
+ "act_bits": 16,
176
+ "act_data_type": "float",
177
+ "bits": 16,
178
+ "data_type": "float",
179
+ "group_size": 128,
180
+ "sym": true
181
+ },
182
+ "model.language_model.layers.28.mlp.gate": {
183
+ "act_bits": 16,
184
+ "act_data_type": "float",
185
+ "bits": 16,
186
+ "data_type": "float",
187
+ "group_size": 128,
188
+ "sym": true
189
+ },
190
+ "model.language_model.layers.29.mlp.gate": {
191
+ "act_bits": 16,
192
+ "act_data_type": "float",
193
+ "bits": 16,
194
+ "data_type": "float",
195
+ "group_size": 128,
196
+ "sym": true
197
+ },
198
+ "model.language_model.layers.3.mlp.gate": {
199
+ "act_bits": 16,
200
+ "act_data_type": "float",
201
+ "bits": 16,
202
+ "data_type": "float",
203
+ "group_size": 128,
204
+ "sym": true
205
+ },
206
+ "model.language_model.layers.30.mlp.gate": {
207
+ "act_bits": 16,
208
+ "act_data_type": "float",
209
+ "bits": 16,
210
+ "data_type": "float",
211
+ "group_size": 128,
212
+ "sym": true
213
+ },
214
+ "model.language_model.layers.31.mlp.gate": {
215
+ "act_bits": 16,
216
+ "act_data_type": "float",
217
+ "bits": 16,
218
+ "data_type": "float",
219
+ "group_size": 128,
220
+ "sym": true
221
+ },
222
+ "model.language_model.layers.32.mlp.gate": {
223
+ "act_bits": 16,
224
+ "act_data_type": "float",
225
+ "bits": 16,
226
+ "data_type": "float",
227
+ "group_size": 128,
228
+ "sym": true
229
+ },
230
+ "model.language_model.layers.33.mlp.gate": {
231
+ "act_bits": 16,
232
+ "act_data_type": "float",
233
+ "bits": 16,
234
+ "data_type": "float",
235
+ "group_size": 128,
236
+ "sym": true
237
+ },
238
+ "model.language_model.layers.34.mlp.gate": {
239
+ "act_bits": 16,
240
+ "act_data_type": "float",
241
+ "bits": 16,
242
+ "data_type": "float",
243
+ "group_size": 128,
244
+ "sym": true
245
+ },
246
+ "model.language_model.layers.35.mlp.gate": {
247
+ "act_bits": 16,
248
+ "act_data_type": "float",
249
+ "bits": 16,
250
+ "data_type": "float",
251
+ "group_size": 128,
252
+ "sym": true
253
+ },
254
+ "model.language_model.layers.36.mlp.gate": {
255
+ "act_bits": 16,
256
+ "act_data_type": "float",
257
+ "bits": 16,
258
+ "data_type": "float",
259
+ "group_size": 128,
260
+ "sym": true
261
+ },
262
+ "model.language_model.layers.37.mlp.gate": {
263
+ "act_bits": 16,
264
+ "act_data_type": "float",
265
+ "bits": 16,
266
+ "data_type": "float",
267
+ "group_size": 128,
268
+ "sym": true
269
+ },
270
+ "model.language_model.layers.38.mlp.gate": {
271
+ "act_bits": 16,
272
+ "act_data_type": "float",
273
+ "bits": 16,
274
+ "data_type": "float",
275
+ "group_size": 128,
276
+ "sym": true
277
+ },
278
+ "model.language_model.layers.39.mlp.gate": {
279
+ "act_bits": 16,
280
+ "act_data_type": "float",
281
+ "bits": 16,
282
+ "data_type": "float",
283
+ "group_size": 128,
284
+ "sym": true
285
+ },
286
+ "model.language_model.layers.4.mlp.gate": {
287
+ "act_bits": 16,
288
+ "act_data_type": "float",
289
+ "bits": 16,
290
+ "data_type": "float",
291
+ "group_size": 128,
292
+ "sym": true
293
+ },
294
+ "model.language_model.layers.40.mlp.gate": {
295
+ "act_bits": 16,
296
+ "act_data_type": "float",
297
+ "bits": 16,
298
+ "data_type": "float",
299
+ "group_size": 128,
300
+ "sym": true
301
+ },
302
+ "model.language_model.layers.41.mlp.gate": {
303
+ "act_bits": 16,
304
+ "act_data_type": "float",
305
+ "bits": 16,
306
+ "data_type": "float",
307
+ "group_size": 128,
308
+ "sym": true
309
+ },
310
+ "model.language_model.layers.42.mlp.gate": {
311
+ "act_bits": 16,
312
+ "act_data_type": "float",
313
+ "bits": 16,
314
+ "data_type": "float",
315
+ "group_size": 128,
316
+ "sym": true
317
+ },
318
+ "model.language_model.layers.43.mlp.gate": {
319
+ "act_bits": 16,
320
+ "act_data_type": "float",
321
+ "bits": 16,
322
+ "data_type": "float",
323
+ "group_size": 128,
324
+ "sym": true
325
+ },
326
+ "model.language_model.layers.44.mlp.gate": {
327
+ "act_bits": 16,
328
+ "act_data_type": "float",
329
+ "bits": 16,
330
+ "data_type": "float",
331
+ "group_size": 128,
332
+ "sym": true
333
+ },
334
+ "model.language_model.layers.45.mlp.gate": {
335
+ "act_bits": 16,
336
+ "act_data_type": "float",
337
+ "bits": 16,
338
+ "data_type": "float",
339
+ "group_size": 128,
340
+ "sym": true
341
+ },
342
+ "model.language_model.layers.46.mlp.gate": {
343
+ "act_bits": 16,
344
+ "act_data_type": "float",
345
+ "bits": 16,
346
+ "data_type": "float",
347
+ "group_size": 128,
348
+ "sym": true
349
+ },
350
+ "model.language_model.layers.47.mlp.gate": {
351
+ "act_bits": 16,
352
+ "act_data_type": "float",
353
+ "bits": 16,
354
+ "data_type": "float",
355
+ "group_size": 128,
356
+ "sym": true
357
+ },
358
+ "model.language_model.layers.5.mlp.gate": {
359
+ "act_bits": 16,
360
+ "act_data_type": "float",
361
+ "bits": 16,
362
+ "data_type": "float",
363
+ "group_size": 128,
364
+ "sym": true
365
+ },
366
+ "model.language_model.layers.6.mlp.gate": {
367
+ "act_bits": 16,
368
+ "act_data_type": "float",
369
+ "bits": 16,
370
+ "data_type": "float",
371
+ "group_size": 128,
372
+ "sym": true
373
+ },
374
+ "model.language_model.layers.7.mlp.gate": {
375
+ "act_bits": 16,
376
+ "act_data_type": "float",
377
+ "bits": 16,
378
+ "data_type": "float",
379
+ "group_size": 128,
380
+ "sym": true
381
+ },
382
+ "model.language_model.layers.8.mlp.gate": {
383
+ "act_bits": 16,
384
+ "act_data_type": "float",
385
+ "bits": 16,
386
+ "data_type": "float",
387
+ "group_size": 128,
388
+ "sym": true
389
+ },
390
+ "model.language_model.layers.9.mlp.gate": {
391
+ "act_bits": 16,
392
+ "act_data_type": "float",
393
+ "bits": 16,
394
+ "data_type": "float",
395
+ "group_size": 128,
396
+ "sym": true
397
+ }
398
+ },
399
+ "group_size": 128,
400
+ "packing_format": "auto_round:auto_gptq",
401
+ "quant_method": "auto-round",
402
+ "sym": true
403
+ },
404
+ "text_config": {
405
+ "attention_bias": false,
406
+ "attention_dropout": 0.0,
407
+ "bos_token_id": 151643,
408
+ "decoder_sparse_step": 1,
409
+ "dtype": "bfloat16",
410
+ "eos_token_id": 151645,
411
+ "head_dim": 128,
412
+ "hidden_act": "silu",
413
+ "hidden_size": 2048,
414
+ "initializer_range": 0.02,
415
+ "intermediate_size": 6144,
416
+ "max_position_embeddings": 262144,
417
+ "mlp_only_layers": [],
418
+ "model_type": "qwen3_vl_moe_text",
419
+ "moe_intermediate_size": 768,
420
+ "norm_topk_prob": true,
421
+ "num_attention_heads": 32,
422
+ "num_experts": 128,
423
+ "num_experts_per_tok": 8,
424
+ "num_hidden_layers": 48,
425
+ "num_key_value_heads": 4,
426
+ "rms_norm_eps": 1e-06,
427
+ "rope_scaling": {
428
+ "mrope_interleaved": true,
429
+ "mrope_section": [
430
+ 24,
431
+ 20,
432
+ 20
433
+ ],
434
+ "rope_type": "default"
435
+ },
436
+ "rope_theta": 5000000,
437
+ "router_aux_loss_coef": 0.001,
438
+ "use_cache": true,
439
+ "vocab_size": 151936
440
+ },
441
+ "tie_word_embeddings": false,
442
+ "transformers_version": "4.57.1",
443
+ "video_token_id": 151656,
444
+ "vision_config": {
445
+ "deepstack_visual_indexes": [
446
+ 8,
447
+ 16,
448
+ 24
449
+ ],
450
+ "depth": 27,
451
+ "hidden_act": "gelu_pytorch_tanh",
452
+ "hidden_size": 1152,
453
+ "in_channels": 3,
454
+ "initializer_range": 0.02,
455
+ "intermediate_size": 4304,
456
+ "model_type": "qwen3_vl_moe",
457
+ "num_heads": 16,
458
+ "num_position_embeddings": 2304,
459
+ "out_hidden_size": 2048,
460
+ "patch_size": 16,
461
+ "spatial_merge_size": 2,
462
+ "temporal_patch_size": 2
463
+ },
464
+ "vision_end_token_id": 151653,
465
+ "vision_start_token_id": 151652
466
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329a28648927c4afb61fb2984e66472fe7b0b4b67c824b4ca4475f1dfec73b66
3
+ size 5001034176
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64bc08b2ffc571cbb24aa3c01149976db3df3af83abdd80ed213ecc36a13ae2
3
+ size 5002437256
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426339206a88ac68bf1d75a58ab64a7195a998ecdaa4103b6c2a6248c1d3a4e5
3
+ size 5002150216
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3a14cb8a5532a372bd550ac387cdeae63c370c169110fd10fc19284afbc7c11
3
+ size 2881990984
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": null,
26
+ "merge_size": 2,
27
+ "min_pixels": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 16777216,
36
+ "shortest_edge": 65536
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
quantization_config.json ADDED
@@ -0,0 +1,396 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "sym": true,
5
+ "data_type": "int",
6
+ "autoround_version": "0.9.5",
7
+ "block_name_to_quantize": "model.language_model.layers",
8
+ "quant_method": "auto-round",
9
+ "packing_format": "auto_round:auto_gptq",
10
+ "extra_config": {
11
+ "model.language_model.layers.0.mlp.gate": {
12
+ "bits": 16,
13
+ "group_size": 128,
14
+ "sym": true,
15
+ "data_type": "float",
16
+ "act_bits": 16,
17
+ "act_data_type": "float"
18
+ },
19
+ "model.language_model.layers.1.mlp.gate": {
20
+ "bits": 16,
21
+ "group_size": 128,
22
+ "sym": true,
23
+ "data_type": "float",
24
+ "act_bits": 16,
25
+ "act_data_type": "float"
26
+ },
27
+ "model.language_model.layers.2.mlp.gate": {
28
+ "bits": 16,
29
+ "group_size": 128,
30
+ "sym": true,
31
+ "data_type": "float",
32
+ "act_bits": 16,
33
+ "act_data_type": "float"
34
+ },
35
+ "model.language_model.layers.3.mlp.gate": {
36
+ "bits": 16,
37
+ "group_size": 128,
38
+ "sym": true,
39
+ "data_type": "float",
40
+ "act_bits": 16,
41
+ "act_data_type": "float"
42
+ },
43
+ "model.language_model.layers.4.mlp.gate": {
44
+ "bits": 16,
45
+ "group_size": 128,
46
+ "sym": true,
47
+ "data_type": "float",
48
+ "act_bits": 16,
49
+ "act_data_type": "float"
50
+ },
51
+ "model.language_model.layers.5.mlp.gate": {
52
+ "bits": 16,
53
+ "group_size": 128,
54
+ "sym": true,
55
+ "data_type": "float",
56
+ "act_bits": 16,
57
+ "act_data_type": "float"
58
+ },
59
+ "model.language_model.layers.6.mlp.gate": {
60
+ "bits": 16,
61
+ "group_size": 128,
62
+ "sym": true,
63
+ "data_type": "float",
64
+ "act_bits": 16,
65
+ "act_data_type": "float"
66
+ },
67
+ "model.language_model.layers.7.mlp.gate": {
68
+ "bits": 16,
69
+ "group_size": 128,
70
+ "sym": true,
71
+ "data_type": "float",
72
+ "act_bits": 16,
73
+ "act_data_type": "float"
74
+ },
75
+ "model.language_model.layers.8.mlp.gate": {
76
+ "bits": 16,
77
+ "group_size": 128,
78
+ "sym": true,
79
+ "data_type": "float",
80
+ "act_bits": 16,
81
+ "act_data_type": "float"
82
+ },
83
+ "model.language_model.layers.9.mlp.gate": {
84
+ "bits": 16,
85
+ "group_size": 128,
86
+ "sym": true,
87
+ "data_type": "float",
88
+ "act_bits": 16,
89
+ "act_data_type": "float"
90
+ },
91
+ "model.language_model.layers.10.mlp.gate": {
92
+ "bits": 16,
93
+ "group_size": 128,
94
+ "sym": true,
95
+ "data_type": "float",
96
+ "act_bits": 16,
97
+ "act_data_type": "float"
98
+ },
99
+ "model.language_model.layers.11.mlp.gate": {
100
+ "bits": 16,
101
+ "group_size": 128,
102
+ "sym": true,
103
+ "data_type": "float",
104
+ "act_bits": 16,
105
+ "act_data_type": "float"
106
+ },
107
+ "model.language_model.layers.12.mlp.gate": {
108
+ "bits": 16,
109
+ "group_size": 128,
110
+ "sym": true,
111
+ "data_type": "float",
112
+ "act_bits": 16,
113
+ "act_data_type": "float"
114
+ },
115
+ "model.language_model.layers.13.mlp.gate": {
116
+ "bits": 16,
117
+ "group_size": 128,
118
+ "sym": true,
119
+ "data_type": "float",
120
+ "act_bits": 16,
121
+ "act_data_type": "float"
122
+ },
123
+ "model.language_model.layers.14.mlp.gate": {
124
+ "bits": 16,
125
+ "group_size": 128,
126
+ "sym": true,
127
+ "data_type": "float",
128
+ "act_bits": 16,
129
+ "act_data_type": "float"
130
+ },
131
+ "model.language_model.layers.15.mlp.gate": {
132
+ "bits": 16,
133
+ "group_size": 128,
134
+ "sym": true,
135
+ "data_type": "float",
136
+ "act_bits": 16,
137
+ "act_data_type": "float"
138
+ },
139
+ "model.language_model.layers.16.mlp.gate": {
140
+ "bits": 16,
141
+ "group_size": 128,
142
+ "sym": true,
143
+ "data_type": "float",
144
+ "act_bits": 16,
145
+ "act_data_type": "float"
146
+ },
147
+ "model.language_model.layers.17.mlp.gate": {
148
+ "bits": 16,
149
+ "group_size": 128,
150
+ "sym": true,
151
+ "data_type": "float",
152
+ "act_bits": 16,
153
+ "act_data_type": "float"
154
+ },
155
+ "model.language_model.layers.18.mlp.gate": {
156
+ "bits": 16,
157
+ "group_size": 128,
158
+ "sym": true,
159
+ "data_type": "float",
160
+ "act_bits": 16,
161
+ "act_data_type": "float"
162
+ },
163
+ "model.language_model.layers.19.mlp.gate": {
164
+ "bits": 16,
165
+ "group_size": 128,
166
+ "sym": true,
167
+ "data_type": "float",
168
+ "act_bits": 16,
169
+ "act_data_type": "float"
170
+ },
171
+ "model.language_model.layers.20.mlp.gate": {
172
+ "bits": 16,
173
+ "group_size": 128,
174
+ "sym": true,
175
+ "data_type": "float",
176
+ "act_bits": 16,
177
+ "act_data_type": "float"
178
+ },
179
+ "model.language_model.layers.21.mlp.gate": {
180
+ "bits": 16,
181
+ "group_size": 128,
182
+ "sym": true,
183
+ "data_type": "float",
184
+ "act_bits": 16,
185
+ "act_data_type": "float"
186
+ },
187
+ "model.language_model.layers.22.mlp.gate": {
188
+ "bits": 16,
189
+ "group_size": 128,
190
+ "sym": true,
191
+ "data_type": "float",
192
+ "act_bits": 16,
193
+ "act_data_type": "float"
194
+ },
195
+ "model.language_model.layers.23.mlp.gate": {
196
+ "bits": 16,
197
+ "group_size": 128,
198
+ "sym": true,
199
+ "data_type": "float",
200
+ "act_bits": 16,
201
+ "act_data_type": "float"
202
+ },
203
+ "model.language_model.layers.24.mlp.gate": {
204
+ "bits": 16,
205
+ "group_size": 128,
206
+ "sym": true,
207
+ "data_type": "float",
208
+ "act_bits": 16,
209
+ "act_data_type": "float"
210
+ },
211
+ "model.language_model.layers.25.mlp.gate": {
212
+ "bits": 16,
213
+ "group_size": 128,
214
+ "sym": true,
215
+ "data_type": "float",
216
+ "act_bits": 16,
217
+ "act_data_type": "float"
218
+ },
219
+ "model.language_model.layers.26.mlp.gate": {
220
+ "bits": 16,
221
+ "group_size": 128,
222
+ "sym": true,
223
+ "data_type": "float",
224
+ "act_bits": 16,
225
+ "act_data_type": "float"
226
+ },
227
+ "model.language_model.layers.27.mlp.gate": {
228
+ "bits": 16,
229
+ "group_size": 128,
230
+ "sym": true,
231
+ "data_type": "float",
232
+ "act_bits": 16,
233
+ "act_data_type": "float"
234
+ },
235
+ "model.language_model.layers.28.mlp.gate": {
236
+ "bits": 16,
237
+ "group_size": 128,
238
+ "sym": true,
239
+ "data_type": "float",
240
+ "act_bits": 16,
241
+ "act_data_type": "float"
242
+ },
243
+ "model.language_model.layers.29.mlp.gate": {
244
+ "bits": 16,
245
+ "group_size": 128,
246
+ "sym": true,
247
+ "data_type": "float",
248
+ "act_bits": 16,
249
+ "act_data_type": "float"
250
+ },
251
+ "model.language_model.layers.30.mlp.gate": {
252
+ "bits": 16,
253
+ "group_size": 128,
254
+ "sym": true,
255
+ "data_type": "float",
256
+ "act_bits": 16,
257
+ "act_data_type": "float"
258
+ },
259
+ "model.language_model.layers.31.mlp.gate": {
260
+ "bits": 16,
261
+ "group_size": 128,
262
+ "sym": true,
263
+ "data_type": "float",
264
+ "act_bits": 16,
265
+ "act_data_type": "float"
266
+ },
267
+ "model.language_model.layers.32.mlp.gate": {
268
+ "bits": 16,
269
+ "group_size": 128,
270
+ "sym": true,
271
+ "data_type": "float",
272
+ "act_bits": 16,
273
+ "act_data_type": "float"
274
+ },
275
+ "model.language_model.layers.33.mlp.gate": {
276
+ "bits": 16,
277
+ "group_size": 128,
278
+ "sym": true,
279
+ "data_type": "float",
280
+ "act_bits": 16,
281
+ "act_data_type": "float"
282
+ },
283
+ "model.language_model.layers.34.mlp.gate": {
284
+ "bits": 16,
285
+ "group_size": 128,
286
+ "sym": true,
287
+ "data_type": "float",
288
+ "act_bits": 16,
289
+ "act_data_type": "float"
290
+ },
291
+ "model.language_model.layers.35.mlp.gate": {
292
+ "bits": 16,
293
+ "group_size": 128,
294
+ "sym": true,
295
+ "data_type": "float",
296
+ "act_bits": 16,
297
+ "act_data_type": "float"
298
+ },
299
+ "model.language_model.layers.36.mlp.gate": {
300
+ "bits": 16,
301
+ "group_size": 128,
302
+ "sym": true,
303
+ "data_type": "float",
304
+ "act_bits": 16,
305
+ "act_data_type": "float"
306
+ },
307
+ "model.language_model.layers.37.mlp.gate": {
308
+ "bits": 16,
309
+ "group_size": 128,
310
+ "sym": true,
311
+ "data_type": "float",
312
+ "act_bits": 16,
313
+ "act_data_type": "float"
314
+ },
315
+ "model.language_model.layers.38.mlp.gate": {
316
+ "bits": 16,
317
+ "group_size": 128,
318
+ "sym": true,
319
+ "data_type": "float",
320
+ "act_bits": 16,
321
+ "act_data_type": "float"
322
+ },
323
+ "model.language_model.layers.39.mlp.gate": {
324
+ "bits": 16,
325
+ "group_size": 128,
326
+ "sym": true,
327
+ "data_type": "float",
328
+ "act_bits": 16,
329
+ "act_data_type": "float"
330
+ },
331
+ "model.language_model.layers.40.mlp.gate": {
332
+ "bits": 16,
333
+ "group_size": 128,
334
+ "sym": true,
335
+ "data_type": "float",
336
+ "act_bits": 16,
337
+ "act_data_type": "float"
338
+ },
339
+ "model.language_model.layers.41.mlp.gate": {
340
+ "bits": 16,
341
+ "group_size": 128,
342
+ "sym": true,
343
+ "data_type": "float",
344
+ "act_bits": 16,
345
+ "act_data_type": "float"
346
+ },
347
+ "model.language_model.layers.42.mlp.gate": {
348
+ "bits": 16,
349
+ "group_size": 128,
350
+ "sym": true,
351
+ "data_type": "float",
352
+ "act_bits": 16,
353
+ "act_data_type": "float"
354
+ },
355
+ "model.language_model.layers.43.mlp.gate": {
356
+ "bits": 16,
357
+ "group_size": 128,
358
+ "sym": true,
359
+ "data_type": "float",
360
+ "act_bits": 16,
361
+ "act_data_type": "float"
362
+ },
363
+ "model.language_model.layers.44.mlp.gate": {
364
+ "bits": 16,
365
+ "group_size": 128,
366
+ "sym": true,
367
+ "data_type": "float",
368
+ "act_bits": 16,
369
+ "act_data_type": "float"
370
+ },
371
+ "model.language_model.layers.45.mlp.gate": {
372
+ "bits": 16,
373
+ "group_size": 128,
374
+ "sym": true,
375
+ "data_type": "float",
376
+ "act_bits": 16,
377
+ "act_data_type": "float"
378
+ },
379
+ "model.language_model.layers.46.mlp.gate": {
380
+ "bits": 16,
381
+ "group_size": 128,
382
+ "sym": true,
383
+ "data_type": "float",
384
+ "act_bits": 16,
385
+ "act_data_type": "float"
386
+ },
387
+ "model.language_model.layers.47.mlp.gate": {
388
+ "bits": 16,
389
+ "group_size": 128,
390
+ "sym": true,
391
+ "data_type": "float",
392
+ "act_bits": 16,
393
+ "act_data_type": "float"
394
+ }
395
+ }
396
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "processor_class": "Qwen3VLProcessor",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff