Hugging Face's logo

mdh98
/
qwen_classify_model

Safetensors
Model card Files
xet
Community
mdh98 commited on
Commit
1223030
·
verified ·
1 Parent(s): ac1cfd8

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. food172_ls_5e_6_e5/added_tokens.json +24 -0
  3. food172_ls_5e_6_e5/chat_template.jinja +7 -0
  4. food172_ls_5e_6_e5/config.json +482 -0
  5. food172_ls_5e_6_e5/merges.txt +0 -0
  6. food172_ls_5e_6_e5/model-00001-of-00004.safetensors +3 -0
  7. food172_ls_5e_6_e5/model-00002-of-00004.safetensors +3 -0
  8. food172_ls_5e_6_e5/model-00003-of-00004.safetensors +3 -0
  9. food172_ls_5e_6_e5/model-00004-of-00004.safetensors +3 -0
  10. food172_ls_5e_6_e5/model.safetensors.index.json +738 -0
  11. food172_ls_5e_6_e5/preprocessor_config.json +29 -0
  12. food172_ls_5e_6_e5/special_tokens_map.json +31 -0
  13. food172_ls_5e_6_e5/tokenizer.json +3 -0
  14. food172_ls_5e_6_e5/tokenizer_config.json +208 -0
  15. food172_ls_5e_6_e5/training_info.json +91 -0
  16. food172_ls_5e_6_e5/video_preprocessor_config.json +43 -0
  17. food172_ls_5e_6_e5/vocab.json +0 -0
.gitattributes CHANGED
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  food101_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  food2k_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  multi_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
36
  food101_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  food2k_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  multi_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ food172_ls_5e_6_e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
food172_ls_5e_6_e5/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
food172_ls_5e_6_e5/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
food172_ls_5e_6_e5/config.json ADDED
@@ -0,0 +1,482 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForImageClassification"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29",
41
+ "30": "LABEL_30",
42
+ "31": "LABEL_31",
43
+ "32": "LABEL_32",
44
+ "33": "LABEL_33",
45
+ "34": "LABEL_34",
46
+ "35": "LABEL_35",
47
+ "36": "LABEL_36",
48
+ "37": "LABEL_37",
49
+ "38": "LABEL_38",
50
+ "39": "LABEL_39",
51
+ "40": "LABEL_40",
52
+ "41": "LABEL_41",
53
+ "42": "LABEL_42",
54
+ "43": "LABEL_43",
55
+ "44": "LABEL_44",
56
+ "45": "LABEL_45",
57
+ "46": "LABEL_46",
58
+ "47": "LABEL_47",
59
+ "48": "LABEL_48",
60
+ "49": "LABEL_49",
61
+ "50": "LABEL_50",
62
+ "51": "LABEL_51",
63
+ "52": "LABEL_52",
64
+ "53": "LABEL_53",
65
+ "54": "LABEL_54",
66
+ "55": "LABEL_55",
67
+ "56": "LABEL_56",
68
+ "57": "LABEL_57",
69
+ "58": "LABEL_58",
70
+ "59": "LABEL_59",
71
+ "60": "LABEL_60",
72
+ "61": "LABEL_61",
73
+ "62": "LABEL_62",
74
+ "63": "LABEL_63",
75
+ "64": "LABEL_64",
76
+ "65": "LABEL_65",
77
+ "66": "LABEL_66",
78
+ "67": "LABEL_67",
79
+ "68": "LABEL_68",
80
+ "69": "LABEL_69",
81
+ "70": "LABEL_70",
82
+ "71": "LABEL_71",
83
+ "72": "LABEL_72",
84
+ "73": "LABEL_73",
85
+ "74": "LABEL_74",
86
+ "75": "LABEL_75",
87
+ "76": "LABEL_76",
88
+ "77": "LABEL_77",
89
+ "78": "LABEL_78",
90
+ "79": "LABEL_79",
91
+ "80": "LABEL_80",
92
+ "81": "LABEL_81",
93
+ "82": "LABEL_82",
94
+ "83": "LABEL_83",
95
+ "84": "LABEL_84",
96
+ "85": "LABEL_85",
97
+ "86": "LABEL_86",
98
+ "87": "LABEL_87",
99
+ "88": "LABEL_88",
100
+ "89": "LABEL_89",
101
+ "90": "LABEL_90",
102
+ "91": "LABEL_91",
103
+ "92": "LABEL_92",
104
+ "93": "LABEL_93",
105
+ "94": "LABEL_94",
106
+ "95": "LABEL_95",
107
+ "96": "LABEL_96",
108
+ "97": "LABEL_97",
109
+ "98": "LABEL_98",
110
+ "99": "LABEL_99",
111
+ "100": "LABEL_100",
112
+ "101": "LABEL_101",
113
+ "102": "LABEL_102",
114
+ "103": "LABEL_103",
115
+ "104": "LABEL_104",
116
+ "105": "LABEL_105",
117
+ "106": "LABEL_106",
118
+ "107": "LABEL_107",
119
+ "108": "LABEL_108",
120
+ "109": "LABEL_109",
121
+ "110": "LABEL_110",
122
+ "111": "LABEL_111",
123
+ "112": "LABEL_112",
124
+ "113": "LABEL_113",
125
+ "114": "LABEL_114",
126
+ "115": "LABEL_115",
127
+ "116": "LABEL_116",
128
+ "117": "LABEL_117",
129
+ "118": "LABEL_118",
130
+ "119": "LABEL_119",
131
+ "120": "LABEL_120",
132
+ "121": "LABEL_121",
133
+ "122": "LABEL_122",
134
+ "123": "LABEL_123",
135
+ "124": "LABEL_124",
136
+ "125": "LABEL_125",
137
+ "126": "LABEL_126",
138
+ "127": "LABEL_127",
139
+ "128": "LABEL_128",
140
+ "129": "LABEL_129",
141
+ "130": "LABEL_130",
142
+ "131": "LABEL_131",
143
+ "132": "LABEL_132",
144
+ "133": "LABEL_133",
145
+ "134": "LABEL_134",
146
+ "135": "LABEL_135",
147
+ "136": "LABEL_136",
148
+ "137": "LABEL_137",
149
+ "138": "LABEL_138",
150
+ "139": "LABEL_139",
151
+ "140": "LABEL_140",
152
+ "141": "LABEL_141",
153
+ "142": "LABEL_142",
154
+ "143": "LABEL_143",
155
+ "144": "LABEL_144",
156
+ "145": "LABEL_145",
157
+ "146": "LABEL_146",
158
+ "147": "LABEL_147",
159
+ "148": "LABEL_148",
160
+ "149": "LABEL_149",
161
+ "150": "LABEL_150",
162
+ "151": "LABEL_151",
163
+ "152": "LABEL_152",
164
+ "153": "LABEL_153",
165
+ "154": "LABEL_154",
166
+ "155": "LABEL_155",
167
+ "156": "LABEL_156",
168
+ "157": "LABEL_157",
169
+ "158": "LABEL_158",
170
+ "159": "LABEL_159",
171
+ "160": "LABEL_160",
172
+ "161": "LABEL_161",
173
+ "162": "LABEL_162",
174
+ "163": "LABEL_163",
175
+ "164": "LABEL_164",
176
+ "165": "LABEL_165",
177
+ "166": "LABEL_166",
178
+ "167": "LABEL_167",
179
+ "168": "LABEL_168",
180
+ "169": "LABEL_169",
181
+ "170": "LABEL_170",
182
+ "171": "LABEL_171"
183
+ },
184
+ "image_token_id": 151655,
185
+ "initializer_range": 0.02,
186
+ "intermediate_size": 18944,
187
+ "label2id": {
188
+ "LABEL_0": 0,
189
+ "LABEL_1": 1,
190
+ "LABEL_10": 10,
191
+ "LABEL_100": 100,
192
+ "LABEL_101": 101,
193
+ "LABEL_102": 102,
194
+ "LABEL_103": 103,
195
+ "LABEL_104": 104,
196
+ "LABEL_105": 105,
197
+ "LABEL_106": 106,
198
+ "LABEL_107": 107,
199
+ "LABEL_108": 108,
200
+ "LABEL_109": 109,
201
+ "LABEL_11": 11,
202
+ "LABEL_110": 110,
203
+ "LABEL_111": 111,
204
+ "LABEL_112": 112,
205
+ "LABEL_113": 113,
206
+ "LABEL_114": 114,
207
+ "LABEL_115": 115,
208
+ "LABEL_116": 116,
209
+ "LABEL_117": 117,
210
+ "LABEL_118": 118,
211
+ "LABEL_119": 119,
212
+ "LABEL_12": 12,
213
+ "LABEL_120": 120,
214
+ "LABEL_121": 121,
215
+ "LABEL_122": 122,
216
+ "LABEL_123": 123,
217
+ "LABEL_124": 124,
218
+ "LABEL_125": 125,
219
+ "LABEL_126": 126,
220
+ "LABEL_127": 127,
221
+ "LABEL_128": 128,
222
+ "LABEL_129": 129,
223
+ "LABEL_13": 13,
224
+ "LABEL_130": 130,
225
+ "LABEL_131": 131,
226
+ "LABEL_132": 132,
227
+ "LABEL_133": 133,
228
+ "LABEL_134": 134,
229
+ "LABEL_135": 135,
230
+ "LABEL_136": 136,
231
+ "LABEL_137": 137,
232
+ "LABEL_138": 138,
233
+ "LABEL_139": 139,
234
+ "LABEL_14": 14,
235
+ "LABEL_140": 140,
236
+ "LABEL_141": 141,
237
+ "LABEL_142": 142,
238
+ "LABEL_143": 143,
239
+ "LABEL_144": 144,
240
+ "LABEL_145": 145,
241
+ "LABEL_146": 146,
242
+ "LABEL_147": 147,
243
+ "LABEL_148": 148,
244
+ "LABEL_149": 149,
245
+ "LABEL_15": 15,
246
+ "LABEL_150": 150,
247
+ "LABEL_151": 151,
248
+ "LABEL_152": 152,
249
+ "LABEL_153": 153,
250
+ "LABEL_154": 154,
251
+ "LABEL_155": 155,
252
+ "LABEL_156": 156,
253
+ "LABEL_157": 157,
254
+ "LABEL_158": 158,
255
+ "LABEL_159": 159,
256
+ "LABEL_16": 16,
257
+ "LABEL_160": 160,
258
+ "LABEL_161": 161,
259
+ "LABEL_162": 162,
260
+ "LABEL_163": 163,
261
+ "LABEL_164": 164,
262
+ "LABEL_165": 165,
263
+ "LABEL_166": 166,
264
+ "LABEL_167": 167,
265
+ "LABEL_168": 168,
266
+ "LABEL_169": 169,
267
+ "LABEL_17": 17,
268
+ "LABEL_170": 170,
269
+ "LABEL_171": 171,
270
+ "LABEL_18": 18,
271
+ "LABEL_19": 19,
272
+ "LABEL_2": 2,
273
+ "LABEL_20": 20,
274
+ "LABEL_21": 21,
275
+ "LABEL_22": 22,
276
+ "LABEL_23": 23,
277
+ "LABEL_24": 24,
278
+ "LABEL_25": 25,
279
+ "LABEL_26": 26,
280
+ "LABEL_27": 27,
281
+ "LABEL_28": 28,
282
+ "LABEL_29": 29,
283
+ "LABEL_3": 3,
284
+ "LABEL_30": 30,
285
+ "LABEL_31": 31,
286
+ "LABEL_32": 32,
287
+ "LABEL_33": 33,
288
+ "LABEL_34": 34,
289
+ "LABEL_35": 35,
290
+ "LABEL_36": 36,
291
+ "LABEL_37": 37,
292
+ "LABEL_38": 38,
293
+ "LABEL_39": 39,
294
+ "LABEL_4": 4,
295
+ "LABEL_40": 40,
296
+ "LABEL_41": 41,
297
+ "LABEL_42": 42,
298
+ "LABEL_43": 43,
299
+ "LABEL_44": 44,
300
+ "LABEL_45": 45,
301
+ "LABEL_46": 46,
302
+ "LABEL_47": 47,
303
+ "LABEL_48": 48,
304
+ "LABEL_49": 49,
305
+ "LABEL_5": 5,
306
+ "LABEL_50": 50,
307
+ "LABEL_51": 51,
308
+ "LABEL_52": 52,
309
+ "LABEL_53": 53,
310
+ "LABEL_54": 54,
311
+ "LABEL_55": 55,
312
+ "LABEL_56": 56,
313
+ "LABEL_57": 57,
314
+ "LABEL_58": 58,
315
+ "LABEL_59": 59,
316
+ "LABEL_6": 6,
317
+ "LABEL_60": 60,
318
+ "LABEL_61": 61,
319
+ "LABEL_62": 62,
320
+ "LABEL_63": 63,
321
+ "LABEL_64": 64,
322
+ "LABEL_65": 65,
323
+ "LABEL_66": 66,
324
+ "LABEL_67": 67,
325
+ "LABEL_68": 68,
326
+ "LABEL_69": 69,
327
+ "LABEL_7": 7,
328
+ "LABEL_70": 70,
329
+ "LABEL_71": 71,
330
+ "LABEL_72": 72,
331
+ "LABEL_73": 73,
332
+ "LABEL_74": 74,
333
+ "LABEL_75": 75,
334
+ "LABEL_76": 76,
335
+ "LABEL_77": 77,
336
+ "LABEL_78": 78,
337
+ "LABEL_79": 79,
338
+ "LABEL_8": 8,
339
+ "LABEL_80": 80,
340
+ "LABEL_81": 81,
341
+ "LABEL_82": 82,
342
+ "LABEL_83": 83,
343
+ "LABEL_84": 84,
344
+ "LABEL_85": 85,
345
+ "LABEL_86": 86,
346
+ "LABEL_87": 87,
347
+ "LABEL_88": 88,
348
+ "LABEL_89": 89,
349
+ "LABEL_9": 9,
350
+ "LABEL_90": 90,
351
+ "LABEL_91": 91,
352
+ "LABEL_92": 92,
353
+ "LABEL_93": 93,
354
+ "LABEL_94": 94,
355
+ "LABEL_95": 95,
356
+ "LABEL_96": 96,
357
+ "LABEL_97": 97,
358
+ "LABEL_98": 98,
359
+ "LABEL_99": 99
360
+ },
361
+ "max_position_embeddings": 128000,
362
+ "max_window_layers": 28,
363
+ "model_type": "qwen2_5_vl",
364
+ "num_attention_heads": 28,
365
+ "num_hidden_layers": 28,
366
+ "num_key_value_heads": 4,
367
+ "rms_norm_eps": 1e-06,
368
+ "rope_scaling": {
369
+ "mrope_section": [
370
+ 16,
371
+ 24,
372
+ 24
373
+ ],
374
+ "rope_type": "default",
375
+ "type": "default"
376
+ },
377
+ "rope_theta": 1000000.0,
378
+ "sliding_window": 32768,
379
+ "text_config": {
380
+ "architectures": [
381
+ "Qwen2_5_VLForConditionalGeneration"
382
+ ],
383
+ "attention_dropout": 0.0,
384
+ "bos_token_id": 151643,
385
+ "eos_token_id": 151645,
386
+ "hidden_act": "silu",
387
+ "hidden_size": 3584,
388
+ "image_token_id": null,
389
+ "initializer_range": 0.02,
390
+ "intermediate_size": 18944,
391
+ "layer_types": [
392
+ "full_attention",
393
+ "full_attention",
394
+ "full_attention",
395
+ "full_attention",
396
+ "full_attention",
397
+ "full_attention",
398
+ "full_attention",
399
+ "full_attention",
400
+ "full_attention",
401
+ "full_attention",
402
+ "full_attention",
403
+ "full_attention",
404
+ "full_attention",
405
+ "full_attention",
406
+ "full_attention",
407
+ "full_attention",
408
+ "full_attention",
409
+ "full_attention",
410
+ "full_attention",
411
+ "full_attention",
412
+ "full_attention",
413
+ "full_attention",
414
+ "full_attention",
415
+ "full_attention",
416
+ "full_attention",
417
+ "full_attention",
418
+ "full_attention",
419
+ "full_attention"
420
+ ],
421
+ "max_position_embeddings": 128000,
422
+ "max_window_layers": 28,
423
+ "model_type": "qwen2_5_vl_text",
424
+ "num_attention_heads": 28,
425
+ "num_hidden_layers": 28,
426
+ "num_key_value_heads": 4,
427
+ "rms_norm_eps": 1e-06,
428
+ "rope_scaling": {
429
+ "mrope_section": [
430
+ 16,
431
+ 24,
432
+ 24
433
+ ],
434
+ "rope_type": "default",
435
+ "type": "default"
436
+ },
437
+ "rope_theta": 1000000.0,
438
+ "sliding_window": null,
439
+ "torch_dtype": "bfloat16",
440
+ "use_cache": true,
441
+ "use_sliding_window": false,
442
+ "video_token_id": null,
443
+ "vision_end_token_id": 151653,
444
+ "vision_start_token_id": 151652,
445
+ "vision_token_id": 151654,
446
+ "vocab_size": 152064
447
+ },
448
+ "tie_word_embeddings": false,
449
+ "torch_dtype": "bfloat16",
450
+ "transformers_version": "4.54.0.dev0",
451
+ "use_cache": false,
452
+ "use_sliding_window": false,
453
+ "video_token_id": 151656,
454
+ "vision_config": {
455
+ "depth": 32,
456
+ "fullatt_block_indexes": [
457
+ 7,
458
+ 15,
459
+ 23,
460
+ 31
461
+ ],
462
+ "hidden_act": "silu",
463
+ "hidden_size": 1280,
464
+ "in_channels": 3,
465
+ "in_chans": 3,
466
+ "initializer_range": 0.02,
467
+ "intermediate_size": 3420,
468
+ "model_type": "qwen2_5_vl",
469
+ "num_heads": 16,
470
+ "out_hidden_size": 3584,
471
+ "patch_size": 14,
472
+ "spatial_merge_size": 2,
473
+ "spatial_patch_size": 14,
474
+ "temporal_patch_size": 2,
475
+ "tokens_per_second": 2,
476
+ "window_size": 112
477
+ },
478
+ "vision_end_token_id": 151653,
479
+ "vision_start_token_id": 151652,
480
+ "vision_token_id": 151654,
481
+ "vocab_size": 152064
482
+ }
food172_ls_5e_6_e5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
food172_ls_5e_6_e5/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9776025c0b3fb5524703896d9db06665ca8894ee1bfbbcb416a7ffab81c7959
3
+ size 4968246672
food172_ls_5e_6_e5/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3146d6e94d3e0b5d7aebf7b8bbfdeb1ee9357e5ccc245d3ab64926e9d947d10e
3
+ size 4991497784
food172_ls_5e_6_e5/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67fbb6a4533f704275072107090d941247d338924167fb95d6b1fb6994f01aa
3
+ size 4932752872
food172_ls_5e_6_e5/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80bc569a2e96db76560702b2fcba644c30deec6da45d5ef965d33b5186193b17
3
+ size 603163144
food172_ls_5e_6_e5/model.safetensors.index.json ADDED
@@ -0,0 +1,738 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 7747785900,
4
+ "total_size": 15495571800
5
+ },
6
+ "weight_map": {
7
+ "classifier.bias": "model-00004-of-00004.safetensors",
8
+ "classifier.weight": "model-00004-of-00004.safetensors",
9
+ "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
10
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
11
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
15
+ "model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
16
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
21
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
27
+ "model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
28
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
33
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.language_model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
40
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.language_model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.language_model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
45
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.language_model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
52
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.language_model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.language_model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
57
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.language_model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
64
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.language_model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.language_model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
69
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
71
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "model.language_model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
76
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.language_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.language_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
81
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
83
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.language_model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
88
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.language_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.language_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
93
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.language_model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
100
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.language_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.language_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
105
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "model.language_model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
112
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.language_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.language_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
117
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
119
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
122
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
123
+ "model.language_model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
124
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.language_model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.language_model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
129
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.language_model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
136
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.language_model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.language_model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
141
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
147
+ "model.language_model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
148
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.language_model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.language_model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
153
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
155
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
158
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
159
+ "model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
160
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
165
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
166
+ "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.language_model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
172
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.language_model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.language_model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
177
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
183
+ "model.language_model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
184
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.language_model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.language_model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
189
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
191
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "model.language_model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
196
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.language_model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.language_model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
201
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.language_model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
208
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.language_model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.language_model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
213
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
215
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "model.language_model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
220
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.language_model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.language_model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
225
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
227
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
231
+ "model.language_model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
232
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.language_model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.language_model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
237
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
240
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
243
+ "model.language_model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
244
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.language_model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.language_model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
249
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
251
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
254
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
255
+ "model.language_model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
256
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.language_model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.language_model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
261
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
262
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
268
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
273
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
280
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
285
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
287
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
291
+ "model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
292
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
297
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
299
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
302
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
303
+ "model.language_model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
304
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.language_model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.language_model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
309
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
311
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
314
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
315
+ "model.language_model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
316
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.language_model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.language_model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
321
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
323
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
326
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
327
+ "model.language_model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
328
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.language_model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.language_model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
333
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
335
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
338
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
339
+ "model.language_model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
340
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.language_model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.language_model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
345
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
346
+ "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
347
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
348
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
350
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
351
+ "model.visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
352
+ "model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
354
+ "model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
355
+ "model.visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
356
+ "model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
358
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
359
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
360
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
361
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
362
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
363
+ "model.visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
364
+ "model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
366
+ "model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
367
+ "model.visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
368
+ "model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
369
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
370
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
371
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
372
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
373
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
374
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
375
+ "model.visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
376
+ "model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
377
+ "model.visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
378
+ "model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
379
+ "model.visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
380
+ "model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
381
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
382
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
383
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
384
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
386
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
387
+ "model.visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
388
+ "model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
389
+ "model.visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
390
+ "model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
392
+ "model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
393
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
394
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
395
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
396
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
397
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
398
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
399
+ "model.visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
400
+ "model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
401
+ "model.visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
402
+ "model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
403
+ "model.visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
404
+ "model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
405
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
406
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
407
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
408
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
409
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
410
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
411
+ "model.visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
412
+ "model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
413
+ "model.visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
414
+ "model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
415
+ "model.visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
416
+ "model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
417
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
418
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
419
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
420
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
421
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
422
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
423
+ "model.visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
424
+ "model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
425
+ "model.visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
426
+ "model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
427
+ "model.visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
428
+ "model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
429
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
430
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
431
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
432
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
433
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
434
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
435
+ "model.visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
436
+ "model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
437
+ "model.visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
438
+ "model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
439
+ "model.visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
440
+ "model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
441
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
442
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
443
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
444
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
445
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
446
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
447
+ "model.visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
448
+ "model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
449
+ "model.visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
450
+ "model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
451
+ "model.visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
452
+ "model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
453
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
454
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
455
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
456
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
457
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
458
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
459
+ "model.visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
460
+ "model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
461
+ "model.visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
462
+ "model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
463
+ "model.visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
464
+ "model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
465
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
466
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
467
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
468
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
469
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
470
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
471
+ "model.visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
472
+ "model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
473
+ "model.visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
474
+ "model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
475
+ "model.visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
476
+ "model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
477
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
478
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
479
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
480
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
481
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
482
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
483
+ "model.visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
484
+ "model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
485
+ "model.visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
486
+ "model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
487
+ "model.visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
488
+ "model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
489
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
490
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
491
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
492
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
493
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
494
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
495
+ "model.visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
496
+ "model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
497
+ "model.visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
498
+ "model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
499
+ "model.visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
500
+ "model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
501
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
502
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
503
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
504
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
505
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
506
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
507
+ "model.visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
508
+ "model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
509
+ "model.visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
510
+ "model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
511
+ "model.visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
512
+ "model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
513
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
514
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
515
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
516
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
517
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
518
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
519
+ "model.visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
520
+ "model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
521
+ "model.visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
522
+ "model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
523
+ "model.visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
524
+ "model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
525
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
526
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
527
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
528
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
529
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
530
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
531
+ "model.visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
532
+ "model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
533
+ "model.visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
534
+ "model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
535
+ "model.visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
536
+ "model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
537
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
538
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
539
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
540
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
541
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
542
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
543
+ "model.visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
544
+ "model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
545
+ "model.visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
546
+ "model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
547
+ "model.visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
548
+ "model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
549
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
550
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
551
+ "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
552
+ "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
553
+ "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
554
+ "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
555
+ "model.visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
556
+ "model.visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
557
+ "model.visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
558
+ "model.visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
559
+ "model.visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
560
+ "model.visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
561
+ "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
562
+ "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
563
+ "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
564
+ "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
565
+ "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
566
+ "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
567
+ "model.visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
568
+ "model.visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
569
+ "model.visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
570
+ "model.visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
571
+ "model.visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
572
+ "model.visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
573
+ "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
574
+ "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
575
+ "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
576
+ "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
577
+ "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
578
+ "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
579
+ "model.visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
580
+ "model.visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
581
+ "model.visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
582
+ "model.visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
583
+ "model.visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
584
+ "model.visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
585
+ "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
586
+ "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
587
+ "model.visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
588
+ "model.visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
589
+ "model.visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
590
+ "model.visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
591
+ "model.visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
592
+ "model.visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
593
+ "model.visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
594
+ "model.visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
595
+ "model.visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
596
+ "model.visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
597
+ "model.visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
598
+ "model.visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
599
+ "model.visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
600
+ "model.visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
601
+ "model.visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
602
+ "model.visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
603
+ "model.visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
604
+ "model.visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
605
+ "model.visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
606
+ "model.visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
607
+ "model.visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
608
+ "model.visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
609
+ "model.visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
610
+ "model.visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
611
+ "model.visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
612
+ "model.visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
613
+ "model.visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
614
+ "model.visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
615
+ "model.visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
616
+ "model.visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
617
+ "model.visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
618
+ "model.visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
619
+ "model.visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
620
+ "model.visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
621
+ "model.visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
622
+ "model.visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
623
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
624
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
625
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
626
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
627
+ "model.visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
628
+ "model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
629
+ "model.visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
630
+ "model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
631
+ "model.visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
632
+ "model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
633
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
634
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
635
+ "model.visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
636
+ "model.visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
637
+ "model.visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
638
+ "model.visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
639
+ "model.visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
640
+ "model.visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
641
+ "model.visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
642
+ "model.visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
643
+ "model.visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
644
+ "model.visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
645
+ "model.visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
646
+ "model.visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
647
+ "model.visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
648
+ "model.visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
649
+ "model.visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
650
+ "model.visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
651
+ "model.visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
652
+ "model.visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
653
+ "model.visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
654
+ "model.visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
655
+ "model.visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
656
+ "model.visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
657
+ "model.visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
658
+ "model.visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
659
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
660
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
661
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
662
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
663
+ "model.visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
664
+ "model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
665
+ "model.visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
666
+ "model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
667
+ "model.visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
668
+ "model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
669
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
670
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
671
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
672
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
673
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
674
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
675
+ "model.visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
676
+ "model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
677
+ "model.visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
678
+ "model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
679
+ "model.visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
680
+ "model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
681
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
682
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
683
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
684
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
685
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
686
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
687
+ "model.visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
688
+ "model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
689
+ "model.visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
690
+ "model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
691
+ "model.visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
692
+ "model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
693
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
694
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
695
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
696
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
697
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
698
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
699
+ "model.visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
700
+ "model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
701
+ "model.visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
702
+ "model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
703
+ "model.visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
704
+ "model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
705
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
706
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
707
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
708
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
709
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
710
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
711
+ "model.visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
712
+ "model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
713
+ "model.visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
714
+ "model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
715
+ "model.visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
716
+ "model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
717
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
718
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
719
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
720
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
721
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
722
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
723
+ "model.visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
724
+ "model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
725
+ "model.visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
726
+ "model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
727
+ "model.visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
728
+ "model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
729
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
730
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
731
+ "model.visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
732
+ "model.visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
733
+ "model.visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
734
+ "model.visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
735
+ "model.visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
736
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
737
+ }
738
+ }
food172_ls_5e_6_e5/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
food172_ls_5e_6_e5/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
+ }
food172_ls_5e_6_e5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
food172_ls_5e_6_e5/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
food172_ls_5e_6_e5/training_info.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 5160,
3
+ "epoch": 4,
4
+ "config": {
5
+ "model": {
6
+ "pretrained_name": "/llm_reco/dehua/model/Qwen2.5-VL-7B-Instruct",
7
+ "num_labels": 172
8
+ },
9
+ "loss": {
10
+ "type": "label_smoothing",
11
+ "smoothing": 0.1,
12
+ "temperature": 1.0
13
+ },
14
+ "datasets": {
15
+ "dataset_configs": {
16
+ "food172": {
17
+ "num_classes": 172,
18
+ "description": "Food172 dataset",
19
+ "eval_ratio": 1
20
+ }
21
+ },
22
+ "enable_logits_masking": false,
23
+ "shuffle_datasets": false
24
+ },
25
+ "data": {
26
+ "train_jsonl": "/llm_reco/dehua/code/qwen_classify/data/dataset_food_label/food172_train.jsonl",
27
+ "val_jsonl": "/llm_reco/dehua/code/qwen_classify/data/dataset_food_label/food172_test.jsonl"
28
+ },
29
+ "training": {
30
+ "epochs": 5,
31
+ "lr": "5e-6",
32
+ "weight_decay": 0.01,
33
+ "warmup_steps": 200,
34
+ "output_dir": "/mmu_mllm_hdd_2/madehua/model/qwen_classify/food172_ls_5e_6",
35
+ "logging_steps": 5000,
36
+ "save_steps": 200,
37
+ "eval_steps": 200,
38
+ "save_hf_format": true,
39
+ "save_deepspeed_format": false,
40
+ "num_workers": 32,
41
+ "use_fused_adam": true,
42
+ "lr_scheduler": {
43
+ "type": "cosine",
44
+ "final_lr_ratio": 0.1,
45
+ "num_cycles": 0.5
46
+ },
47
+ "best_model_tracking": {
48
+ "enabled": true,
49
+ "metric": "overall_accuracy",
50
+ "mode": "max",
51
+ "save_best_only": true
52
+ },
53
+ "evaluation": {
54
+ "partial_eval_during_training": true,
55
+ "full_eval_at_end": true,
56
+ "eval_best_model_only": true
57
+ },
58
+ "num_epochs": 5,
59
+ "learning_rate": "5e-6"
60
+ },
61
+ "deepspeed": "configs/ds_s2.json",
62
+ "wandb": {
63
+ "enabled": true,
64
+ "project": "qwen_classification",
65
+ "run_name": "food172_cosine_5e_6_ls",
66
+ "tags": [
67
+ "qwen",
68
+ "deepspeed",
69
+ "classification",
70
+ "cosine_hold",
71
+ "single_dataset"
72
+ ],
73
+ "notes": "Qwen2.5-VL Food101 classification with cosine+hold scheduler",
74
+ "log_dataset_metrics": false,
75
+ "log_overall_metrics": true
76
+ },
77
+ "accelerate": {
78
+ "bf16": true
79
+ },
80
+ "output_dir": "/mmu_mllm_hdd_2/madehua/model/qwen_classify/food172_ls_5e_6",
81
+ "logging_steps": 5000,
82
+ "save_steps": 200,
83
+ "eval_steps": 200,
84
+ "save_hf_format": true,
85
+ "save_deepspeed_format": false
86
+ },
87
+ "dataset_metrics": {},
88
+ "is_best_model": true,
89
+ "best_metric_value": 0.9237635705669481,
90
+ "timestamp": 1752654319.4142358
91
+ }
food172_ls_5e_6_e5/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "size": {
36
+ "longest_edge": 12845056,
37
+ "shortest_edge": 3136
38
+ },
39
+ "size_divisor": null,
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
food172_ls_5e_6_e5/vocab.json ADDED
The diff for this file is too large to render. See raw diff