File size: 66,006 Bytes
92b6d07
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
{
  "metadata": {
    "total_size": 18357448972
  },
  "weight_map": {
    "vlm.lang_model.lm_head.additional_fc.bias": "model-00004-of-00004.safetensors",
    "vlm.lang_model.lm_head.additional_fc.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.lm_head.bias": "model-00004-of-00004.safetensors",
    "vlm.lang_model.lm_head.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.embed_tokens.additional_embedding.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.25.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
    "vlm.lang_model.model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.27.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.28.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.28.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.29.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.29.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.3.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.lang_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.30.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.30.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.31.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.31.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
    "vlm.lang_model.model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.4.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.4.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.5.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.6.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
    "vlm.lang_model.model.norm.weight": "model-00004-of-00004.safetensors",
    "vlm.vision_encoder.class_embedding": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.conv1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.ln_post.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.ln_post.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.ln_pre.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.ln_pre.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.positional_embedding": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.proj": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.20.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.21.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.22.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.23.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.24.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.25.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.26.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.27.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.28.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.29.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.30.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.31.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.ln_1.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.ln_1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.ln_2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.ln_2.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_encoder.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.latents": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.norm_latents.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.norm_latents.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.norm_media.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.norm_media.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.to_kv.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.to_out.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.0.to_q.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.1.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.1.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.1.1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.0.1.3.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.norm_latents.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.norm_latents.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.norm_media.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.norm_media.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.to_kv.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.to_out.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.0.to_q.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.1.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.1.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.1.1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.1.1.3.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.norm_latents.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.norm_latents.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.norm_media.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.norm_media.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.to_kv.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.to_out.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.0.to_q.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.1.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.1.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.1.1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.2.1.3.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.norm_latents.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.norm_latents.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.norm_media.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.norm_media.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.to_kv.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.to_out.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.0.to_q.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.1.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.1.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.1.1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.3.1.3.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.norm_latents.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.norm_latents.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.norm_media.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.norm_media.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.to_kv.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.to_out.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.0.to_q.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.1.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.1.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.1.1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.4.1.3.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.norm_latents.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.norm_latents.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.norm_media.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.norm_media.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.to_kv.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.to_out.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.0.to_q.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.1.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.1.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.1.1.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.layers.5.1.3.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.norm.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.norm.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.projection.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.projection.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.text_projection.0.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.text_projection.0.weight": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.text_projection.2.bias": "model-00001-of-00004.safetensors",
    "vlm.vision_tokenizer.text_projection.2.weight": "model-00001-of-00004.safetensors"
  }
}