liuhuijie6410 commited on
Commit
5bbe167
·
verified ·
1 Parent(s): 0fd8b4a

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
codebook/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f3a583c016bd97fe0c0c553bbe82d785070784fc48b266ee984f663fb89b13
3
+ size 285263750
freq.json ADDED
@@ -0,0 +1,947 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "15": 30958,
3
+ "528": 24319,
4
+ "737": 16080,
5
+ "17": 20457,
6
+ "322": 31713,
7
+ "441": 50777,
8
+ "599": 121555,
9
+ "569": 35107,
10
+ "25": 35268,
11
+ "807": 30422,
12
+ "68": 67492,
13
+ "396": 47334,
14
+ "636": 24451,
15
+ "963": 17154,
16
+ "814": 15772,
17
+ "171": 15838,
18
+ "14": 13305,
19
+ "303": 13763,
20
+ "974": 16100,
21
+ "295": 19060,
22
+ "471": 26105,
23
+ "332": 63924,
24
+ "666": 17508,
25
+ "183": 43222,
26
+ "787": 14189,
27
+ "364": 18435,
28
+ "722": 21779,
29
+ "186": 18909,
30
+ "199": 32633,
31
+ "936": 45112,
32
+ "245": 25691,
33
+ "394": 32402,
34
+ "622": 18432,
35
+ "564": 10147,
36
+ "505": 80761,
37
+ "93": 32371,
38
+ "875": 17803,
39
+ "825": 46336,
40
+ "998": 45855,
41
+ "566": 132043,
42
+ "74": 104781,
43
+ "574": 8866,
44
+ "423": 25834,
45
+ "187": 39679,
46
+ "422": 57688,
47
+ "763": 44790,
48
+ "184": 41999,
49
+ "597": 30659,
50
+ "119": 30917,
51
+ "158": 31723,
52
+ "969": 27923,
53
+ "592": 21987,
54
+ "828": 35150,
55
+ "360": 54436,
56
+ "43": 22976,
57
+ "660": 11025,
58
+ "26": 15219,
59
+ "275": 18658,
60
+ "300": 19333,
61
+ "519": 22735,
62
+ "889": 90363,
63
+ "768": 9508,
64
+ "373": 19857,
65
+ "623": 133571,
66
+ "292": 13616,
67
+ "833": 21351,
68
+ "443": 24819,
69
+ "1015": 22145,
70
+ "682": 18716,
71
+ "588": 16703,
72
+ "222": 25145,
73
+ "783": 3193,
74
+ "140": 37533,
75
+ "392": 26872,
76
+ "57": 4826,
77
+ "484": 19868,
78
+ "960": 45714,
79
+ "260": 22691,
80
+ "342": 25770,
81
+ "32": 19073,
82
+ "651": 28829,
83
+ "752": 21908,
84
+ "181": 14955,
85
+ "613": 14399,
86
+ "765": 17968,
87
+ "931": 16338,
88
+ "289": 14008,
89
+ "311": 35796,
90
+ "1007": 28751,
91
+ "41": 7841,
92
+ "28": 47224,
93
+ "831": 28910,
94
+ "837": 15767,
95
+ "399": 22581,
96
+ "694": 25962,
97
+ "766": 31274,
98
+ "678": 11849,
99
+ "589": 35253,
100
+ "53": 30916,
101
+ "643": 26638,
102
+ "288": 33587,
103
+ "445": 16452,
104
+ "540": 70874,
105
+ "524": 18379,
106
+ "954": 14243,
107
+ "415": 32348,
108
+ "155": 11186,
109
+ "601": 15012,
110
+ "2": 26209,
111
+ "642": 32213,
112
+ "325": 38546,
113
+ "434": 92716,
114
+ "494": 51197,
115
+ "244": 43523,
116
+ "727": 31072,
117
+ "747": 48161,
118
+ "410": 17655,
119
+ "467": 12145,
120
+ "887": 165272,
121
+ "989": 30807,
122
+ "503": 45250,
123
+ "857": 28886,
124
+ "291": 10178,
125
+ "361": 16462,
126
+ "4": 44644,
127
+ "400": 40580,
128
+ "1020": 18316,
129
+ "150": 31079,
130
+ "197": 102620,
131
+ "376": 52863,
132
+ "39": 73313,
133
+ "645": 15338,
134
+ "416": 56799,
135
+ "933": 29659,
136
+ "658": 203,
137
+ "164": 79233,
138
+ "902": 38611,
139
+ "226": 73817,
140
+ "577": 30150,
141
+ "418": 10510,
142
+ "201": 29003,
143
+ "270": 28497,
144
+ "780": 45010,
145
+ "527": 76591,
146
+ "806": 730,
147
+ "776": 73346,
148
+ "801": 66703,
149
+ "473": 16124,
150
+ "594": 24251,
151
+ "738": 26365,
152
+ "812": 23968,
153
+ "958": 28504,
154
+ "773": 17546,
155
+ "69": 18106,
156
+ "160": 22863,
157
+ "797": 32823,
158
+ "873": 9922,
159
+ "788": 21198,
160
+ "827": 25590,
161
+ "457": 39682,
162
+ "309": 26370,
163
+ "67": 10686,
164
+ "668": 39845,
165
+ "470": 26640,
166
+ "736": 20013,
167
+ "653": 58352,
168
+ "732": 67515,
169
+ "231": 46200,
170
+ "75": 46149,
171
+ "629": 13845,
172
+ "225": 12639,
173
+ "516": 12668,
174
+ "617": 28412,
175
+ "946": 53602,
176
+ "999": 20280,
177
+ "811": 34171,
178
+ "924": 29496,
179
+ "143": 9567,
180
+ "294": 12314,
181
+ "255": 11170,
182
+ "576": 10809,
183
+ "917": 20075,
184
+ "572": 21636,
185
+ "560": 895,
186
+ "172": 44619,
187
+ "535": 41924,
188
+ "234": 24065,
189
+ "848": 19348,
190
+ "0": 21045,
191
+ "161": 73876,
192
+ "1008": 20000,
193
+ "707": 60331,
194
+ "256": 82646,
195
+ "547": 66910,
196
+ "202": 25715,
197
+ "648": 38408,
198
+ "542": 16626,
199
+ "561": 13991,
200
+ "55": 30445,
201
+ "508": 18599,
202
+ "923": 7921,
203
+ "688": 33827,
204
+ "29": 14155,
205
+ "481": 26015,
206
+ "407": 6258,
207
+ "681": 22167,
208
+ "988": 13936,
209
+ "537": 13971,
210
+ "56": 87498,
211
+ "211": 10140,
212
+ "173": 19907,
213
+ "871": 24833,
214
+ "567": 19608,
215
+ "320": 10248,
216
+ "699": 24001,
217
+ "571": 13122,
218
+ "726": 17689,
219
+ "286": 7784,
220
+ "845": 8789,
221
+ "677": 26225,
222
+ "584": 21989,
223
+ "262": 17536,
224
+ "728": 11708,
225
+ "626": 15395,
226
+ "296": 18134,
227
+ "263": 13337,
228
+ "778": 23853,
229
+ "856": 23213,
230
+ "813": 12070,
231
+ "628": 12005,
232
+ "968": 15161,
233
+ "293": 12373,
234
+ "334": 19347,
235
+ "177": 18530,
236
+ "90": 9730,
237
+ "916": 18916,
238
+ "111": 22616,
239
+ "829": 20661,
240
+ "977": 49301,
241
+ "961": 21898,
242
+ "19": 10489,
243
+ "862": 20693,
244
+ "131": 14044,
245
+ "459": 22513,
246
+ "912": 19545,
247
+ "138": 21016,
248
+ "23": 44581,
249
+ "525": 14504,
250
+ "276": 14897,
251
+ "649": 19322,
252
+ "705": 62335,
253
+ "672": 51602,
254
+ "791": 28363,
255
+ "454": 32071,
256
+ "607": 9449,
257
+ "852": 12411,
258
+ "192": 22359,
259
+ "460": 34086,
260
+ "431": 18655,
261
+ "925": 16038,
262
+ "44": 6589,
263
+ "943": 12832,
264
+ "769": 18539,
265
+ "489": 7035,
266
+ "586": 13853,
267
+ "755": 20252,
268
+ "905": 18638,
269
+ "476": 33663,
270
+ "7": 7614,
271
+ "339": 7540,
272
+ "333": 18657,
273
+ "555": 54349,
274
+ "427": 21817,
275
+ "664": 52081,
276
+ "864": 31265,
277
+ "79": 9429,
278
+ "302": 20597,
279
+ "233": 32805,
280
+ "414": 11474,
281
+ "775": 16305,
282
+ "104": 6091,
283
+ "662": 12371,
284
+ "704": 21670,
285
+ "546": 21764,
286
+ "639": 4821,
287
+ "109": 9613,
288
+ "1011": 5085,
289
+ "80": 9158,
290
+ "488": 21545,
291
+ "83": 13766,
292
+ "820": 16559,
293
+ "335": 14441,
294
+ "683": 16903,
295
+ "35": 24564,
296
+ "913": 7136,
297
+ "796": 109519,
298
+ "898": 18388,
299
+ "591": 25187,
300
+ "522": 13024,
301
+ "327": 24603,
302
+ "502": 13721,
303
+ "975": 7531,
304
+ "751": 14863,
305
+ "604": 17784,
306
+ "501": 16415,
307
+ "809": 12929,
308
+ "357": 98444,
309
+ "492": 79393,
310
+ "108": 12799,
311
+ "338": 24163,
312
+ "719": 12577,
313
+ "994": 4357,
314
+ "745": 33223,
315
+ "793": 11260,
316
+ "955": 20303,
317
+ "606": 15857,
318
+ "886": 24553,
319
+ "708": 11832,
320
+ "972": 18754,
321
+ "190": 18709,
322
+ "240": 12667,
323
+ "377": 25496,
324
+ "877": 22095,
325
+ "500": 14947,
326
+ "883": 16853,
327
+ "927": 14196,
328
+ "518": 14876,
329
+ "515": 8435,
330
+ "95": 79146,
331
+ "926": 10810,
332
+ "739": 18246,
333
+ "770": 5368,
334
+ "16": 20419,
335
+ "771": 8244,
336
+ "180": 7619,
337
+ "45": 26423,
338
+ "1017": 27585,
339
+ "235": 24725,
340
+ "496": 11790,
341
+ "541": 3692,
342
+ "227": 9120,
343
+ "477": 48858,
344
+ "78": 8480,
345
+ "30": 24978,
346
+ "307": 15258,
347
+ "507": 8094,
348
+ "520": 23730,
349
+ "198": 20350,
350
+ "343": 19403,
351
+ "46": 16826,
352
+ "822": 15116,
353
+ "463": 16155,
354
+ "88": 10445,
355
+ "930": 18084,
356
+ "785": 14039,
357
+ "356": 21090,
358
+ "50": 23884,
359
+ "714": 8499,
360
+ "428": 49747,
361
+ "358": 33417,
362
+ "123": 33540,
363
+ "654": 29123,
364
+ "209": 44334,
365
+ "258": 51340,
366
+ "627": 25579,
367
+ "859": 13120,
368
+ "552": 25123,
369
+ "674": 38457,
370
+ "810": 11137,
371
+ "64": 32307,
372
+ "965": 17656,
373
+ "1012": 18796,
374
+ "344": 24172,
375
+ "781": 20006,
376
+ "86": 23180,
377
+ "675": 12828,
378
+ "718": 39483,
379
+ "269": 20691,
380
+ "478": 17236,
381
+ "638": 47315,
382
+ "175": 4871,
383
+ "124": 17469,
384
+ "659": 15444,
385
+ "725": 17602,
386
+ "695": 11915,
387
+ "836": 21935,
388
+ "31": 15767,
389
+ "237": 22314,
390
+ "205": 61038,
391
+ "382": 20482,
392
+ "583": 47172,
393
+ "687": 12584,
394
+ "153": 54809,
395
+ "749": 12063,
396
+ "453": 15357,
397
+ "84": 12110,
398
+ "844": 29896,
399
+ "611": 8807,
400
+ "24": 10422,
401
+ "319": 12270,
402
+ "995": 9679,
403
+ "532": 10713,
404
+ "935": 39019,
405
+ "468": 9633,
406
+ "1013": 4235,
407
+ "287": 15146,
408
+ "145": 9548,
409
+ "832": 17815,
410
+ "784": 15509,
411
+ "826": 13059,
412
+ "206": 21521,
413
+ "130": 18218,
414
+ "616": 10950,
415
+ "669": 43652,
416
+ "526": 13866,
417
+ "99": 33170,
418
+ "777": 11928,
419
+ "72": 18643,
420
+ "821": 12497,
421
+ "301": 39654,
422
+ "655": 16470,
423
+ "448": 18606,
424
+ "485": 26916,
425
+ "277": 12200,
426
+ "253": 15493,
427
+ "840": 45694,
428
+ "375": 9978,
429
+ "876": 24462,
430
+ "609": 12230,
431
+ "249": 26153,
432
+ "248": 42167,
433
+ "920": 10123,
434
+ "151": 30862,
435
+ "266": 23637,
436
+ "268": 6888,
437
+ "497": 6998,
438
+ "890": 9498,
439
+ "744": 6043,
440
+ "159": 15864,
441
+ "8": 21879,
442
+ "154": 20317,
443
+ "469": 5970,
444
+ "563": 29001,
445
+ "421": 4276,
446
+ "600": 12825,
447
+ "590": 69147,
448
+ "670": 9541,
449
+ "562": 12514,
450
+ "701": 46497,
451
+ "73": 13193,
452
+ "841": 9703,
453
+ "318": 18156,
454
+ "71": 9231,
455
+ "348": 26387,
456
+ "439": 46691,
457
+ "896": 14901,
458
+ "466": 26382,
459
+ "386": 32215,
460
+ "646": 7342,
461
+ "362": 26694,
462
+ "419": 27717,
463
+ "250": 15686,
464
+ "136": 25728,
465
+ "907": 28893,
466
+ "133": 7076,
467
+ "290": 8867,
468
+ "782": 36308,
469
+ "163": 28322,
470
+ "684": 16995,
471
+ "1": 76355,
472
+ "408": 179,
473
+ "42": 13314,
474
+ "61": 18699,
475
+ "976": 2961,
476
+ "409": 15593,
477
+ "345": 30447,
478
+ "531": 10292,
479
+ "1005": 25912,
480
+ "962": 87,
481
+ "436": 11840,
482
+ "575": 15407,
483
+ "800": 24861,
484
+ "938": 22045,
485
+ "9": 24953,
486
+ "65": 17582,
487
+ "103": 9568,
488
+ "433": 24387,
489
+ "182": 8382,
490
+ "1023": 10941,
491
+ "461": 19786,
492
+ "215": 16883,
493
+ "573": 21747,
494
+ "897": 7898,
495
+ "482": 9477,
496
+ "10": 20680,
497
+ "412": 33977,
498
+ "634": 25173,
499
+ "696": 30475,
500
+ "993": 20139,
501
+ "605": 34235,
502
+ "495": 10075,
503
+ "894": 35335,
504
+ "731": 15806,
505
+ "81": 28843,
506
+ "665": 39096,
507
+ "506": 5972,
508
+ "401": 14233,
509
+ "789": 18005,
510
+ "236": 11747,
511
+ "869": 19421,
512
+ "746": 23866,
513
+ "51": 42994,
514
+ "858": 31285,
515
+ "650": 18179,
516
+ "188": 11402,
517
+ "980": 15653,
518
+ "932": 19836,
519
+ "305": 9010,
520
+ "1009": 29276,
521
+ "711": 8882,
522
+ "799": 16216,
523
+ "351": 27382,
524
+ "129": 30960,
525
+ "982": 16086,
526
+ "565": 38290,
527
+ "548": 19753,
528
+ "724": 23872,
529
+ "141": 33044,
530
+ "370": 541,
531
+ "953": 12092,
532
+ "849": 7615,
533
+ "966": 7549,
534
+ "824": 5623,
535
+ "34": 39469,
536
+ "474": 9325,
537
+ "758": 15972,
538
+ "456": 9006,
539
+ "451": 20928,
540
+ "193": 11294,
541
+ "189": 19636,
542
+ "247": 9960,
543
+ "940": 15246,
544
+ "504": 20211,
545
+ "12": 18469,
546
+ "842": 51762,
547
+ "217": 9312,
548
+ "216": 17286,
549
+ "558": 12626,
550
+ "838": 16807,
551
+ "967": 20953,
552
+ "6": 15424,
553
+ "585": 41900,
554
+ "115": 9745,
555
+ "139": 4534,
556
+ "259": 16818,
557
+ "170": 35015,
558
+ "116": 27854,
559
+ "380": 10537,
560
+ "355": 11943,
561
+ "750": 18643,
562
+ "934": 30985,
563
+ "637": 13935,
564
+ "308": 15353,
565
+ "38": 12664,
566
+ "218": 18426,
567
+ "350": 18353,
568
+ "228": 23096,
569
+ "283": 18863,
570
+ "420": 18809,
571
+ "465": 19781,
572
+ "389": 13651,
573
+ "855": 26177,
574
+ "40": 19274,
575
+ "735": 31314,
576
+ "657": 7950,
577
+ "685": 3768,
578
+ "819": 12967,
579
+ "861": 37099,
580
+ "48": 10378,
581
+ "663": 15412,
582
+ "347": 5032,
583
+ "381": 23685,
584
+ "102": 25498,
585
+ "242": 8087,
586
+ "280": 16679,
587
+ "539": 8205,
588
+ "63": 28323,
589
+ "843": 12356,
590
+ "536": 3000,
591
+ "425": 13670,
592
+ "1001": 29399,
593
+ "578": 6035,
594
+ "706": 27562,
595
+ "440": 17756,
596
+ "839": 13667,
597
+ "313": 16416,
598
+ "359": 39206,
599
+ "529": 8056,
600
+ "846": 10231,
601
+ "458": 18744,
602
+ "644": 12581,
603
+ "132": 9320,
604
+ "550": 16510,
605
+ "721": 4532,
606
+ "530": 40402,
607
+ "676": 13175,
608
+ "697": 7915,
609
+ "499": 9148,
610
+ "378": 22111,
611
+ "18": 38964,
612
+ "224": 13825,
613
+ "633": 11814,
614
+ "371": 10553,
615
+ "847": 8049,
616
+ "85": 8072,
617
+ "33": 4997,
618
+ "970": 13752,
619
+ "983": 18206,
620
+ "614": 10584,
621
+ "792": 20071,
622
+ "349": 9465,
623
+ "220": 6466,
624
+ "879": 9972,
625
+ "59": 8027,
626
+ "221": 4785,
627
+ "872": 5136,
628
+ "941": 13330,
629
+ "232": 9580,
630
+ "512": 5302,
631
+ "212": 10184,
632
+ "113": 10328,
633
+ "620": 11926,
634
+ "850": 5735,
635
+ "178": 10992,
636
+ "533": 15907,
637
+ "612": 6478,
638
+ "169": 15144,
639
+ "545": 24790,
640
+ "710": 15785,
641
+ "385": 44046,
642
+ "49": 13674,
643
+ "759": 7437,
644
+ "772": 18153,
645
+ "27": 5362,
646
+ "700": 13168,
647
+ "487": 9004,
648
+ "757": 8931,
649
+ "429": 33592,
650
+ "939": 10472,
651
+ "282": 12419,
652
+ "475": 27537,
653
+ "956": 10608,
654
+ "251": 7049,
655
+ "899": 13644,
656
+ "948": 38551,
657
+ "523": 14890,
658
+ "910": 16538,
659
+ "37": 26235,
660
+ "229": 18075,
661
+ "246": 8799,
662
+ "200": 18055,
663
+ "5": 13151,
664
+ "91": 19009,
665
+ "579": 19402,
666
+ "329": 34534,
667
+ "884": 6962,
668
+ "328": 16035,
669
+ "984": 5309,
670
+ "241": 4568,
671
+ "703": 15246,
672
+ "860": 9096,
673
+ "804": 19641,
674
+ "444": 3600,
675
+ "1016": 17315,
676
+ "942": 6685,
677
+ "117": 10234,
678
+ "369": 14753,
679
+ "760": 12489,
680
+ "893": 4168,
681
+ "82": 1172,
682
+ "690": 3832,
683
+ "851": 116,
684
+ "866": 2760,
685
+ "598": 7537,
686
+ "393": 10185,
687
+ "534": 6630,
688
+ "452": 10959,
689
+ "110": 13281,
690
+ "903": 5219,
691
+ "98": 9246,
692
+ "179": 16749,
693
+ "1018": 12451,
694
+ "413": 957,
695
+ "135": 9571,
696
+ "816": 9238,
697
+ "330": 11951,
698
+ "602": 6080,
699
+ "315": 20624,
700
+ "191": 14265,
701
+ "118": 5314,
702
+ "388": 7709,
703
+ "863": 7462,
704
+ "978": 8847,
705
+ "582": 10017,
706
+ "395": 8912,
707
+ "447": 10278,
708
+ "892": 15735,
709
+ "742": 10292,
710
+ "1010": 8345,
711
+ "753": 5069,
712
+ "152": 17000,
713
+ "195": 10775,
714
+ "865": 44699,
715
+ "77": 7422,
716
+ "823": 1444,
717
+ "491": 6423,
718
+ "802": 5333,
719
+ "587": 12849,
720
+ "438": 5713,
721
+ "767": 4833,
722
+ "391": 8173,
723
+ "985": 4352,
724
+ "122": 161,
725
+ "21": 15019,
726
+ "756": 4809,
727
+ "430": 4756,
728
+ "203": 5706,
729
+ "324": 5209,
730
+ "686": 5159,
731
+ "194": 10692,
732
+ "830": 6472,
733
+ "929": 16501,
734
+ "979": 7847,
735
+ "709": 9949,
736
+ "165": 156,
737
+ "730": 991,
738
+ "835": 3374,
739
+ "284": 2288,
740
+ "66": 347,
741
+ "3": 7881,
742
+ "723": 6043,
743
+ "261": 7105,
744
+ "734": 2558,
745
+ "511": 6782,
746
+ "379": 5176,
747
+ "715": 2744,
748
+ "97": 4517,
749
+ "661": 6144,
750
+ "717": 8064,
751
+ "691": 11886,
752
+ "631": 4857,
753
+ "1014": 7419,
754
+ "185": 4831,
755
+ "239": 1370,
756
+ "62": 106,
757
+ "299": 1320,
758
+ "647": 188,
759
+ "882": 1024,
760
+ "314": 890,
761
+ "76": 698,
762
+ "92": 6589,
763
+ "252": 6,
764
+ "341": 64,
765
+ "673": 4667,
766
+ "915": 199,
767
+ "733": 1107,
768
+ "196": 5649,
769
+ "581": 173,
770
+ "880": 453,
771
+ "945": 411,
772
+ "971": 23,
773
+ "964": 3,
774
+ "874": 233,
775
+ "272": 185,
776
+ "442": 129,
777
+ "107": 59,
778
+ "914": 250,
779
+ "867": 20,
780
+ "121": 229,
781
+ "619": 9,
782
+ "168": 659,
783
+ "729": 3,
784
+ "137": 17,
785
+ "987": 362,
786
+ "608": 143,
787
+ "105": 82,
788
+ "952": 17,
789
+ "323": 7,
790
+ "219": 21,
791
+ "556": 136,
792
+ "774": 83,
793
+ "346": 61,
794
+ "630": 128,
795
+ "146": 96,
796
+ "304": 24,
797
+ "693": 81,
798
+ "549": 2,
799
+ "922": 32,
800
+ "279": 24,
801
+ "424": 21,
802
+ "1022": 58,
803
+ "257": 37,
804
+ "127": 39,
805
+ "748": 5,
806
+ "449": 43,
807
+ "405": 21,
808
+ "741": 195,
809
+ "878": 35,
810
+ "278": 76,
811
+ "593": 91,
812
+ "387": 61,
813
+ "538": 7,
814
+ "490": 101,
815
+ "480": 7,
816
+ "267": 20,
817
+ "632": 52,
818
+ "22": 30,
819
+ "641": 52,
820
+ "157": 14,
821
+ "383": 34,
822
+ "52": 15,
823
+ "951": 42,
824
+ "230": 8,
825
+ "543": 52,
826
+ "437": 11,
827
+ "557": 62,
828
+ "509": 56,
829
+ "853": 5,
830
+ "615": 96,
831
+ "621": 24,
832
+ "559": 48,
833
+ "363": 49,
834
+ "156": 12,
835
+ "635": 3,
836
+ "317": 8,
837
+ "624": 10,
838
+ "166": 4,
839
+ "374": 60,
840
+ "554": 4,
841
+ "100": 3,
842
+ "795": 4,
843
+ "435": 52,
844
+ "404": 4,
845
+ "36": 2,
846
+ "656": 11,
847
+ "712": 8,
848
+ "514": 4,
849
+ "973": 1,
850
+ "464": 41,
851
+ "336": 23,
852
+ "603": 4,
853
+ "992": 2,
854
+ "937": 1,
855
+ "406": 17,
856
+ "134": 15,
857
+ "551": 3,
858
+ "213": 5,
859
+ "625": 18,
860
+ "1006": 2,
861
+ "959": 8,
862
+ "208": 1,
863
+ "510": 6,
864
+ "11": 13,
865
+ "689": 13,
866
+ "114": 2,
867
+ "450": 11,
868
+ "513": 1,
869
+ "580": 5,
870
+ "312": 9,
871
+ "702": 1,
872
+ "618": 8,
873
+ "921": 2,
874
+ "207": 2,
875
+ "13": 2,
876
+ "720": 3,
877
+ "326": 5,
878
+ "384": 3,
879
+ "366": 8,
880
+ "274": 4,
881
+ "667": 9,
882
+ "918": 2,
883
+ "716": 14,
884
+ "446": 2,
885
+ "904": 5,
886
+ "908": 2,
887
+ "223": 4,
888
+ "210": 6,
889
+ "803": 1,
890
+ "271": 15,
891
+ "888": 2,
892
+ "1003": 2,
893
+ "112": 4,
894
+ "254": 4,
895
+ "365": 9,
896
+ "544": 3,
897
+ "680": 7,
898
+ "870": 5,
899
+ "671": 4,
900
+ "321": 1,
901
+ "372": 1,
902
+ "310": 2,
903
+ "354": 2,
904
+ "243": 2,
905
+ "996": 1,
906
+ "20": 1,
907
+ "868": 2,
908
+ "949": 1,
909
+ "298": 1,
910
+ "47": 3,
911
+ "553": 1,
912
+ "94": 1,
913
+ "743": 2,
914
+ "698": 1,
915
+ "60": 1,
916
+ "986": 1,
917
+ "794": 3,
918
+ "147": 2,
919
+ "398": 2,
920
+ "238": 2,
921
+ "764": 3,
922
+ "337": 5,
923
+ "640": 2,
924
+ "316": 3,
925
+ "149": 1,
926
+ "148": 1,
927
+ "70": 1,
928
+ "498": 1,
929
+ "805": 1,
930
+ "128": 1,
931
+ "472": 1,
932
+ "285": 1,
933
+ "144": 3,
934
+ "281": 2,
935
+ "652": 1,
936
+ "997": 1,
937
+ "1004": 1,
938
+ "352": 1,
939
+ "297": 1,
940
+ "900": 2,
941
+ "1000": 1,
942
+ "1002": 1,
943
+ "815": 1,
944
+ "568": 1,
945
+ "610": 1,
946
+ "944": 1
947
+ }
model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImagePipeline",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "FlowMatchEulerDiscreteScheduler"
7
+ ],
8
+ "text_encoder": [
9
+ "transformers",
10
+ "Qwen2_5_VLForConditionalGeneration"
11
+ ],
12
+ "tokenizer": [
13
+ "transformers",
14
+ "Qwen2Tokenizer"
15
+ ],
16
+ "transformer": [
17
+ "diffusers",
18
+ "QwenImageTransformer2DModel"
19
+ ],
20
+ "vae": [
21
+ "diffusers",
22
+ "AutoencoderKLQwenImage"
23
+ ]
24
+ }
prior/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 24,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 14,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 32768,
21
+ "tie_word_embeddings": true,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.40.1",
24
+ "use_cache": true,
25
+ "use_mrope": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 1024
28
+ }
prior/prior.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee682f17613ef942f6795f31e5df819969c375c686e48aedc3d09359b0f65fa
3
+ size 717686674
processor/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
+ }
processor/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
processor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
processor/preprocessor_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessorFast",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_pixels": 200704,
25
+ "merge_size": 2,
26
+ "min_pixels": 50176,
27
+ "patch_size": 14,
28
+ "processor_class": "Qwen2VLProcessor",
29
+ "resample": 3,
30
+ "rescale_factor": 0.00392156862745098,
31
+ "return_tensors": null,
32
+ "size": {
33
+ "longest_edge": 12845056,
34
+ "shortest_edge": 3136
35
+ },
36
+ "temporal_patch_size": 2
37
+ }
processor/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
+ }
processor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
processor/tokenizer_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "max_pixels": 200704,
204
+ "min_pixels": 50176,
205
+ "model_max_length": 131072,
206
+ "pad_token": "<|endoftext|>",
207
+ "processor_class": "Qwen2VLProcessor",
208
+ "split_special_tokens": false,
209
+ "tokenizer_class": "Qwen2Tokenizer",
210
+ "unk_token": null
211
+ }
processor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 8192,
8
+ "max_shift": 0.9,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": 0.02,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration_Quant"
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
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "architectures": [
33
+ "Qwen2_5_VLForConditionalGeneration"
34
+ ],
35
+ "attention_dropout": 0.0,
36
+ "bos_token_id": 151643,
37
+ "eos_token_id": 151645,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 3584,
40
+ "image_token_id": null,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 18944,
43
+ "layer_types": [
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention"
72
+ ],
73
+ "max_position_embeddings": 128000,
74
+ "max_window_layers": 28,
75
+ "model_type": "qwen2_5_vl_text",
76
+ "num_attention_heads": 28,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 4,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": {
81
+ "mrope_section": [
82
+ 16,
83
+ 24,
84
+ 24
85
+ ],
86
+ "rope_type": "default",
87
+ "type": "default"
88
+ },
89
+ "rope_theta": 1000000.0,
90
+ "sliding_window": null,
91
+ "torch_dtype": "float32",
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "video_token_id": null,
95
+ "vision_end_token_id": 151653,
96
+ "vision_start_token_id": 151652,
97
+ "vision_token_id": 151654,
98
+ "vocab_size": 152064
99
+ },
100
+ "tie_word_embeddings": false,
101
+ "torch_dtype": "bfloat16",
102
+ "transformers_version": "4.51.1",
103
+ "use_cache": true,
104
+ "use_sliding_window": false,
105
+ "video_token_id": 151656,
106
+ "vision_config": {
107
+ "depth": 32,
108
+ "fullatt_block_indexes": [
109
+ 7,
110
+ 15,
111
+ 23,
112
+ 31
113
+ ],
114
+ "hidden_act": "silu",
115
+ "hidden_size": 1280,
116
+ "in_channels": 3,
117
+ "in_chans": 3,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3420,
120
+ "model_type": "qwen2_5_vl",
121
+ "num_heads": 16,
122
+ "out_hidden_size": 3584,
123
+ "patch_size": 14,
124
+ "spatial_merge_size": 2,
125
+ "spatial_patch_size": 14,
126
+ "temporal_patch_size": 2,
127
+ "tokens_per_second": 2,
128
+ "torch_dtype": "float32",
129
+ "window_size": 112
130
+ },
131
+ "vision_end_token_id": 151653,
132
+ "vision_start_token_id": 151652,
133
+ "vision_token_id": 151654,
134
+ "vocab_size": 152064
135
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.1,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.51.1"
14
+ }
text_encoder/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4
3
+ size 4968243304
text_encoder/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1830db6908dcc76df3a71492acbcf2b8cac130114cf1f3c2d9edae8de8c6de3
3
+ size 4991495816
text_encoder/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c1807c6d00d7cab94f7db39d4c02ebb8537225ccde383861ac48db97945aa6
3
+ size 4932751040
text_encoder/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b454f2ddba797434b18162fd7291c97ddb7015506cb3f3875f3f924ff8dfd1
3
+ size 601929496
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15494338560
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
240
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
284
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.norm.weight": "model-00004-of-00004.safetensors",
344
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
345
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
346
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
728
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
730
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
733
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
734
+ }
735
+ }
tokenizer/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
+ }
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer/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
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImageTransformer2DModel",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "/mmu-vcg-hdd/caohaoxiang/model/Qwen-Image/transformer",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 16,
8
+ 56,
9
+ 56
10
+ ],
11
+ "guidance_embeds": false,
12
+ "in_channels": 64,
13
+ "joint_attention_dim": 3584,
14
+ "num_attention_heads": 24,
15
+ "num_layers": 60,
16
+ "out_channels": 16,
17
+ "patch_size": 2,
18
+ "pooled_projection_dim": 768
19
+ }
transformer/diffusion_pytorch_model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1aca13c756ea01cb1e1c5c6d43dd77a87ea9d19f777b52219a150e96975357
3
+ size 9973578592
transformer/diffusion_pytorch_model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe2835dccb4b8970d1e22c0f8b986f11344d7c3c3933900561c87b479e10b58
3
+ size 9987326072
transformer/diffusion_pytorch_model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e02101c033e96713dcc1fda5dbf6138a704a89e75834573d94a407fe73a29d
3
+ size 9987307440
transformer/diffusion_pytorch_model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5774464852dbc930fb719db45d3d8435b23fc1fa9f548a894fbe53ab0544cde4
3
+ size 9930685712
transformer/diffusion_pytorch_model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dea7b57e46aab41730942af7c92bfab8f9d87f0461fb453882d6184f08729cc
3
+ size 982130472
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLQwenImage",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "/mmu-vcg-hdd/caohaoxiang/model/Qwen-Image/vae",
5
+ "attn_scales": [],
6
+ "base_dim": 96,
7
+ "dim_mult": [
8
+ 1,
9
+ 2,
10
+ 4,
11
+ 4
12
+ ],
13
+ "dropout": 0.0,
14
+ "latents_mean": [
15
+ -0.7571,
16
+ -0.7089,
17
+ -0.9113,
18
+ 0.1075,
19
+ -0.1745,
20
+ 0.9653,
21
+ -0.1517,
22
+ 1.5508,
23
+ 0.4134,
24
+ -0.0715,
25
+ 0.5517,
26
+ -0.3632,
27
+ -0.1922,
28
+ -0.9497,
29
+ 0.2503,
30
+ -0.2921
31
+ ],
32
+ "latents_std": [
33
+ 2.8184,
34
+ 1.4541,
35
+ 2.3275,
36
+ 2.6558,
37
+ 1.2196,
38
+ 1.7708,
39
+ 2.6052,
40
+ 2.0743,
41
+ 3.2687,
42
+ 2.1526,
43
+ 2.8652,
44
+ 1.5579,
45
+ 1.6382,
46
+ 1.1253,
47
+ 2.8251,
48
+ 1.916
49
+ ],
50
+ "num_res_blocks": 2,
51
+ "temperal_downsample": [
52
+ false,
53
+ true,
54
+ true
55
+ ],
56
+ "z_dim": 16
57
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344
3
+ size 253806966