File size: 97,315 Bytes
f57f413
 
de84e35
f57f413
 
de84e35
 
f57f413
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de84e35
 
 
 
 
f57f413
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de84e35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f57f413
 
 
 
 
 
 
 
 
 
 
 
de84e35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f57f413
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de84e35
 
f57f413
 
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
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
{
  "metadata": {
    "total_size": 145412407296
  },
  "weight_map": {
    "lm_head.weight": "model-00031-of-00031.safetensors",
    "model.embed_tokens.weight": "model_embed_tokens_weight.safetensors",
    "model.layers.0.input_layernorm.weight": "model_layers_0_input_layernorm_weight.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model_layers_0_mlp_down_proj_weight.safetensors",
    "model.layers.0.mlp.gate_proj.weight": "model_layers_0_mlp_gate_proj_weight.safetensors",
    "model.layers.0.mlp.up_proj.weight": "model_layers_0_mlp_up_proj_weight.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model_layers_0_post_attention_layernorm_weight.safetensors",
    "model.layers.0.self_attn.k_proj.bias": "model_layers_0_self_attn_k_proj_bias.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model_layers_0_self_attn_k_proj_weight.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model_layers_0_self_attn_o_proj_weight.safetensors",
    "model.layers.0.self_attn.q_proj.bias": "model_layers_0_self_attn_q_proj_bias.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model_layers_0_self_attn_q_proj_weight.safetensors",
    "model.layers.0.self_attn.v_proj.bias": "model_layers_0_self_attn_v_proj_bias.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model_layers_0_self_attn_v_proj_weight.safetensors",
    "model.layers.10.input_layernorm.weight": "model_layers_10_input_layernorm_weight.safetensors",
    "model.layers.10.mlp.down_proj.weight": "model_layers_10_mlp_down_proj_weight.safetensors",
    "model.layers.10.mlp.gate_proj.weight": "model_layers_10_mlp_gate_proj_weight.safetensors",
    "model.layers.10.mlp.up_proj.weight": "model_layers_10_mlp_up_proj_weight.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model_layers_10_post_attention_layernorm_weight.safetensors",
    "model.layers.10.self_attn.k_proj.bias": "model_layers_10_self_attn_k_proj_bias.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model_layers_10_self_attn_k_proj_weight.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model_layers_10_self_attn_o_proj_weight.safetensors",
    "model.layers.10.self_attn.q_proj.bias": "model_layers_10_self_attn_q_proj_bias.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model_layers_10_self_attn_q_proj_weight.safetensors",
    "model.layers.10.self_attn.v_proj.bias": "model_layers_10_self_attn_v_proj_bias.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model_layers_10_self_attn_v_proj_weight.safetensors",
    "model.layers.11.input_layernorm.weight": "model_layers_11_input_layernorm_weight.safetensors",
    "model.layers.11.mlp.down_proj.weight": "model_layers_11_mlp_down_proj_weight.safetensors",
    "model.layers.11.mlp.gate_proj.weight": "model_layers_11_mlp_gate_proj_weight.safetensors",
    "model.layers.11.mlp.up_proj.weight": "model_layers_11_mlp_up_proj_weight.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model_layers_11_post_attention_layernorm_weight.safetensors",
    "model.layers.11.self_attn.k_proj.bias": "model_layers_11_self_attn_k_proj_bias.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model_layers_11_self_attn_k_proj_weight.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model_layers_11_self_attn_o_proj_weight.safetensors",
    "model.layers.11.self_attn.q_proj.bias": "model_layers_11_self_attn_q_proj_bias.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model_layers_11_self_attn_q_proj_weight.safetensors",
    "model.layers.11.self_attn.v_proj.bias": "model_layers_11_self_attn_v_proj_bias.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model_layers_11_self_attn_v_proj_weight.safetensors",
    "model.layers.12.input_layernorm.weight": "model_layers_12_input_layernorm_weight.safetensors",
    "model.layers.12.mlp.down_proj.weight": "model_layers_12_mlp_down_proj_weight.safetensors",
    "model.layers.12.mlp.gate_proj.weight": "model_layers_12_mlp_gate_proj_weight.safetensors",
    "model.layers.12.mlp.up_proj.weight": "model_layers_12_mlp_up_proj_weight.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model_layers_12_post_attention_layernorm_weight.safetensors",
    "model.layers.12.self_attn.k_proj.bias": "model_layers_12_self_attn_k_proj_bias.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model_layers_12_self_attn_k_proj_weight.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model_layers_12_self_attn_o_proj_weight.safetensors",
    "model.layers.12.self_attn.q_proj.bias": "model_layers_12_self_attn_q_proj_bias.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model_layers_12_self_attn_q_proj_weight.safetensors",
    "model.layers.12.self_attn.v_proj.bias": "model_layers_12_self_attn_v_proj_bias.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model_layers_12_self_attn_v_proj_weight.safetensors",
    "model.layers.13.input_layernorm.weight": "model_layers_13_input_layernorm_weight.safetensors",
    "model.layers.13.mlp.down_proj.weight": "model_layers_13_mlp_down_proj_weight.safetensors",
    "model.layers.13.mlp.gate_proj.weight": "model_layers_13_mlp_gate_proj_weight.safetensors",
    "model.layers.13.mlp.up_proj.weight": "model_layers_13_mlp_up_proj_weight.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model_layers_13_post_attention_layernorm_weight.safetensors",
    "model.layers.13.self_attn.k_proj.bias": "model_layers_13_self_attn_k_proj_bias.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model_layers_13_self_attn_k_proj_weight.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model_layers_13_self_attn_o_proj_weight.safetensors",
    "model.layers.13.self_attn.q_proj.bias": "model_layers_13_self_attn_q_proj_bias.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model_layers_13_self_attn_q_proj_weight.safetensors",
    "model.layers.13.self_attn.v_proj.bias": "model_layers_13_self_attn_v_proj_bias.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model_layers_13_self_attn_v_proj_weight.safetensors",
    "model.layers.14.input_layernorm.weight": "model_layers_14_input_layernorm_weight.safetensors",
    "model.layers.14.mlp.down_proj.weight": "model_layers_14_mlp_down_proj_weight.safetensors",
    "model.layers.14.mlp.gate_proj.weight": "model_layers_14_mlp_gate_proj_weight.safetensors",
    "model.layers.14.mlp.up_proj.weight": "model_layers_14_mlp_up_proj_weight.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model_layers_14_post_attention_layernorm_weight.safetensors",
    "model.layers.14.self_attn.k_proj.bias": "model_layers_14_self_attn_k_proj_bias.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model_layers_14_self_attn_k_proj_weight.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model_layers_14_self_attn_o_proj_weight.safetensors",
    "model.layers.14.self_attn.q_proj.bias": "model_layers_14_self_attn_q_proj_bias.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model_layers_14_self_attn_q_proj_weight.safetensors",
    "model.layers.14.self_attn.v_proj.bias": "model_layers_14_self_attn_v_proj_bias.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model_layers_14_self_attn_v_proj_weight.safetensors",
    "model.layers.15.input_layernorm.weight": "model_layers_15_input_layernorm_weight.safetensors",
    "model.layers.15.mlp.down_proj.weight": "model_layers_15_mlp_down_proj_weight.safetensors",
    "model.layers.15.mlp.gate_proj.weight": "model_layers_15_mlp_gate_proj_weight.safetensors",
    "model.layers.15.mlp.up_proj.weight": "model_layers_15_mlp_up_proj_weight.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model_layers_15_post_attention_layernorm_weight.safetensors",
    "model.layers.15.self_attn.k_proj.bias": "model_layers_15_self_attn_k_proj_bias.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model_layers_15_self_attn_k_proj_weight.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model_layers_15_self_attn_o_proj_weight.safetensors",
    "model.layers.15.self_attn.q_proj.bias": "model_layers_15_self_attn_q_proj_bias.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model_layers_15_self_attn_q_proj_weight.safetensors",
    "model.layers.15.self_attn.v_proj.bias": "model_layers_15_self_attn_v_proj_bias.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model_layers_15_self_attn_v_proj_weight.safetensors",
    "model.layers.16.input_layernorm.weight": "model_layers_16_input_layernorm_weight.safetensors",
    "model.layers.16.mlp.down_proj.weight": "model_layers_16_mlp_down_proj_weight.safetensors",
    "model.layers.16.mlp.gate_proj.weight": "model_layers_16_mlp_gate_proj_weight.safetensors",
    "model.layers.16.mlp.up_proj.weight": "model_layers_16_mlp_up_proj_weight.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model_layers_16_post_attention_layernorm_weight.safetensors",
    "model.layers.16.self_attn.k_proj.bias": "model_layers_16_self_attn_k_proj_bias.safetensors",
    "model.layers.16.self_attn.k_proj.weight": "model_layers_16_self_attn_k_proj_weight.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "model_layers_16_self_attn_o_proj_weight.safetensors",
    "model.layers.16.self_attn.q_proj.bias": "model_layers_16_self_attn_q_proj_bias.safetensors",
    "model.layers.16.self_attn.q_proj.weight": "model_layers_16_self_attn_q_proj_weight.safetensors",
    "model.layers.16.self_attn.v_proj.bias": "model_layers_16_self_attn_v_proj_bias.safetensors",
    "model.layers.16.self_attn.v_proj.weight": "model_layers_16_self_attn_v_proj_weight.safetensors",
    "model.layers.17.input_layernorm.weight": "model_layers_17_input_layernorm_weight.safetensors",
    "model.layers.17.mlp.down_proj.weight": "model_layers_17_mlp_down_proj_weight.safetensors",
    "model.layers.17.mlp.gate_proj.weight": "model_layers_17_mlp_gate_proj_weight.safetensors",
    "model.layers.17.mlp.up_proj.weight": "model_layers_17_mlp_up_proj_weight.safetensors",
    "model.layers.17.post_attention_layernorm.weight": "model_layers_17_post_attention_layernorm_weight.safetensors",
    "model.layers.17.self_attn.k_proj.bias": "model_layers_17_self_attn_k_proj_bias.safetensors",
    "model.layers.17.self_attn.k_proj.weight": "model_layers_17_self_attn_k_proj_weight.safetensors",
    "model.layers.17.self_attn.o_proj.weight": "model_layers_17_self_attn_o_proj_weight.safetensors",
    "model.layers.17.self_attn.q_proj.bias": "model_layers_17_self_attn_q_proj_bias.safetensors",
    "model.layers.17.self_attn.q_proj.weight": "model_layers_17_self_attn_q_proj_weight.safetensors",
    "model.layers.17.self_attn.v_proj.bias": "model_layers_17_self_attn_v_proj_bias.safetensors",
    "model.layers.17.self_attn.v_proj.weight": "model_layers_17_self_attn_v_proj_weight.safetensors",
    "model.layers.18.input_layernorm.weight": "model_layers_18_input_layernorm_weight.safetensors",
    "model.layers.18.mlp.down_proj.weight": "model_layers_18_mlp_down_proj_weight.safetensors",
    "model.layers.18.mlp.gate_proj.weight": "model_layers_18_mlp_gate_proj_weight.safetensors",
    "model.layers.18.mlp.up_proj.weight": "model_layers_18_mlp_up_proj_weight.safetensors",
    "model.layers.18.post_attention_layernorm.weight": "model_layers_18_post_attention_layernorm_weight.safetensors",
    "model.layers.18.self_attn.k_proj.bias": "model_layers_18_self_attn_k_proj_bias.safetensors",
    "model.layers.18.self_attn.k_proj.weight": "model_layers_18_self_attn_k_proj_weight.safetensors",
    "model.layers.18.self_attn.o_proj.weight": "model_layers_18_self_attn_o_proj_weight.safetensors",
    "model.layers.18.self_attn.q_proj.bias": "model_layers_18_self_attn_q_proj_bias.safetensors",
    "model.layers.18.self_attn.q_proj.weight": "model_layers_18_self_attn_q_proj_weight.safetensors",
    "model.layers.18.self_attn.v_proj.bias": "model_layers_18_self_attn_v_proj_bias.safetensors",
    "model.layers.18.self_attn.v_proj.weight": "model_layers_18_self_attn_v_proj_weight.safetensors",
    "model.layers.19.input_layernorm.weight": "model_layers_19_input_layernorm_weight.safetensors",
    "model.layers.19.mlp.down_proj.weight": "model_layers_19_mlp_down_proj_weight.safetensors",
    "model.layers.19.mlp.gate_proj.weight": "model_layers_19_mlp_gate_proj_weight.safetensors",
    "model.layers.19.mlp.up_proj.weight": "model_layers_19_mlp_up_proj_weight.safetensors",
    "model.layers.19.post_attention_layernorm.weight": "model_layers_19_post_attention_layernorm_weight.safetensors",
    "model.layers.19.self_attn.k_proj.bias": "model_layers_19_self_attn_k_proj_bias.safetensors",
    "model.layers.19.self_attn.k_proj.weight": "model_layers_19_self_attn_k_proj_weight.safetensors",
    "model.layers.19.self_attn.o_proj.weight": "model_layers_19_self_attn_o_proj_weight.safetensors",
    "model.layers.19.self_attn.q_proj.bias": "model_layers_19_self_attn_q_proj_bias.safetensors",
    "model.layers.19.self_attn.q_proj.weight": "model_layers_19_self_attn_q_proj_weight.safetensors",
    "model.layers.19.self_attn.v_proj.bias": "model_layers_19_self_attn_v_proj_bias.safetensors",
    "model.layers.19.self_attn.v_proj.weight": "model_layers_19_self_attn_v_proj_weight.safetensors",
    "model.layers.1.input_layernorm.weight": "model_layers_1_input_layernorm_weight.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model_layers_1_mlp_down_proj_weight.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "model_layers_1_mlp_gate_proj_weight.safetensors",
    "model.layers.1.mlp.up_proj.weight": "model_layers_1_mlp_up_proj_weight.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model_layers_1_post_attention_layernorm_weight.safetensors",
    "model.layers.1.self_attn.k_proj.bias": "model_layers_1_self_attn_k_proj_bias.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model_layers_1_self_attn_k_proj_weight.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model_layers_1_self_attn_o_proj_weight.safetensors",
    "model.layers.1.self_attn.q_proj.bias": "model_layers_1_self_attn_q_proj_bias.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model_layers_1_self_attn_q_proj_weight.safetensors",
    "model.layers.1.self_attn.v_proj.bias": "model_layers_1_self_attn_v_proj_bias.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model_layers_1_self_attn_v_proj_weight.safetensors",
    "model.layers.20.input_layernorm.weight": "model_layers_20_input_layernorm_weight.safetensors",
    "model.layers.20.mlp.down_proj.weight": "model_layers_20_mlp_down_proj_weight.safetensors",
    "model.layers.20.mlp.gate_proj.weight": "model_layers_20_mlp_gate_proj_weight.safetensors",
    "model.layers.20.mlp.up_proj.weight": "model_layers_20_mlp_up_proj_weight.safetensors",
    "model.layers.20.post_attention_layernorm.weight": "model_layers_20_post_attention_layernorm_weight.safetensors",
    "model.layers.20.self_attn.k_proj.bias": "model_layers_20_self_attn_k_proj_bias.safetensors",
    "model.layers.20.self_attn.k_proj.weight": "model_layers_20_self_attn_k_proj_weight.safetensors",
    "model.layers.20.self_attn.o_proj.weight": "model_layers_20_self_attn_o_proj_weight.safetensors",
    "model.layers.20.self_attn.q_proj.bias": "model_layers_20_self_attn_q_proj_bias.safetensors",
    "model.layers.20.self_attn.q_proj.weight": "model_layers_20_self_attn_q_proj_weight.safetensors",
    "model.layers.20.self_attn.v_proj.bias": "model_layers_20_self_attn_v_proj_bias.safetensors",
    "model.layers.20.self_attn.v_proj.weight": "model_layers_20_self_attn_v_proj_weight.safetensors",
    "model.layers.21.input_layernorm.weight": "model_layers_21_input_layernorm_weight.safetensors",
    "model.layers.21.mlp.down_proj.weight": "model_layers_21_mlp_down_proj_weight.safetensors",
    "model.layers.21.mlp.gate_proj.weight": "model_layers_21_mlp_gate_proj_weight.safetensors",
    "model.layers.21.mlp.up_proj.weight": "model_layers_21_mlp_up_proj_weight.safetensors",
    "model.layers.21.post_attention_layernorm.weight": "model_layers_21_post_attention_layernorm_weight.safetensors",
    "model.layers.21.self_attn.k_proj.bias": "model_layers_21_self_attn_k_proj_bias.safetensors",
    "model.layers.21.self_attn.k_proj.weight": "model_layers_21_self_attn_k_proj_weight.safetensors",
    "model.layers.21.self_attn.o_proj.weight": "model_layers_21_self_attn_o_proj_weight.safetensors",
    "model.layers.21.self_attn.q_proj.bias": "model_layers_21_self_attn_q_proj_bias.safetensors",
    "model.layers.21.self_attn.q_proj.weight": "model_layers_21_self_attn_q_proj_weight.safetensors",
    "model.layers.21.self_attn.v_proj.bias": "model_layers_21_self_attn_v_proj_bias.safetensors",
    "model.layers.21.self_attn.v_proj.weight": "model_layers_21_self_attn_v_proj_weight.safetensors",
    "model.layers.22.input_layernorm.weight": "model_layers_22_input_layernorm_weight.safetensors",
    "model.layers.22.mlp.down_proj.weight": "model_layers_22_mlp_down_proj_weight.safetensors",
    "model.layers.22.mlp.gate_proj.weight": "model_layers_22_mlp_gate_proj_weight.safetensors",
    "model.layers.22.mlp.up_proj.weight": "model_layers_22_mlp_up_proj_weight.safetensors",
    "model.layers.22.post_attention_layernorm.weight": "model_layers_22_post_attention_layernorm_weight.safetensors",
    "model.layers.22.self_attn.k_proj.bias": "model_layers_22_self_attn_k_proj_bias.safetensors",
    "model.layers.22.self_attn.k_proj.weight": "model_layers_22_self_attn_k_proj_weight.safetensors",
    "model.layers.22.self_attn.o_proj.weight": "model_layers_22_self_attn_o_proj_weight.safetensors",
    "model.layers.22.self_attn.q_proj.bias": "model_layers_22_self_attn_q_proj_bias.safetensors",
    "model.layers.22.self_attn.q_proj.weight": "model_layers_22_self_attn_q_proj_weight.safetensors",
    "model.layers.22.self_attn.v_proj.bias": "model_layers_22_self_attn_v_proj_bias.safetensors",
    "model.layers.22.self_attn.v_proj.weight": "model_layers_22_self_attn_v_proj_weight.safetensors",
    "model.layers.23.input_layernorm.weight": "model_layers_23_input_layernorm_weight.safetensors",
    "model.layers.23.mlp.down_proj.weight": "model_layers_23_mlp_down_proj_weight.safetensors",
    "model.layers.23.mlp.gate_proj.weight": "model_layers_23_mlp_gate_proj_weight.safetensors",
    "model.layers.23.mlp.up_proj.weight": "model_layers_23_mlp_up_proj_weight.safetensors",
    "model.layers.23.post_attention_layernorm.weight": "model_layers_23_post_attention_layernorm_weight.safetensors",
    "model.layers.23.self_attn.k_proj.bias": "model_layers_23_self_attn_k_proj_bias.safetensors",
    "model.layers.23.self_attn.k_proj.weight": "model_layers_23_self_attn_k_proj_weight.safetensors",
    "model.layers.23.self_attn.o_proj.weight": "model_layers_23_self_attn_o_proj_weight.safetensors",
    "model.layers.23.self_attn.q_proj.bias": "model_layers_23_self_attn_q_proj_bias.safetensors",
    "model.layers.23.self_attn.q_proj.weight": "model_layers_23_self_attn_q_proj_weight.safetensors",
    "model.layers.23.self_attn.v_proj.bias": "model_layers_23_self_attn_v_proj_bias.safetensors",
    "model.layers.23.self_attn.v_proj.weight": "model_layers_23_self_attn_v_proj_weight.safetensors",
    "model.layers.24.input_layernorm.weight": "model_layers_24_input_layernorm_weight.safetensors",
    "model.layers.24.mlp.down_proj.weight": "model_layers_24_mlp_down_proj_weight.safetensors",
    "model.layers.24.mlp.gate_proj.weight": "model_layers_24_mlp_gate_proj_weight.safetensors",
    "model.layers.24.mlp.up_proj.weight": "model_layers_24_mlp_up_proj_weight.safetensors",
    "model.layers.24.post_attention_layernorm.weight": "model_layers_24_post_attention_layernorm_weight.safetensors",
    "model.layers.24.self_attn.k_proj.bias": "model_layers_24_self_attn_k_proj_bias.safetensors",
    "model.layers.24.self_attn.k_proj.weight": "model_layers_24_self_attn_k_proj_weight.safetensors",
    "model.layers.24.self_attn.o_proj.weight": "model_layers_24_self_attn_o_proj_weight.safetensors",
    "model.layers.24.self_attn.q_proj.bias": "model_layers_24_self_attn_q_proj_bias.safetensors",
    "model.layers.24.self_attn.q_proj.weight": "model_layers_24_self_attn_q_proj_weight.safetensors",
    "model.layers.24.self_attn.v_proj.bias": "model_layers_24_self_attn_v_proj_bias.safetensors",
    "model.layers.24.self_attn.v_proj.weight": "model_layers_24_self_attn_v_proj_weight.safetensors",
    "model.layers.25.input_layernorm.weight": "model_layers_25_input_layernorm_weight.safetensors",
    "model.layers.25.mlp.down_proj.weight": "model_layers_25_mlp_down_proj_weight.safetensors",
    "model.layers.25.mlp.gate_proj.weight": "model_layers_25_mlp_gate_proj_weight.safetensors",
    "model.layers.25.mlp.up_proj.weight": "model_layers_25_mlp_up_proj_weight.safetensors",
    "model.layers.25.post_attention_layernorm.weight": "model_layers_25_post_attention_layernorm_weight.safetensors",
    "model.layers.25.self_attn.k_proj.bias": "model_layers_25_self_attn_k_proj_bias.safetensors",
    "model.layers.25.self_attn.k_proj.weight": "model_layers_25_self_attn_k_proj_weight.safetensors",
    "model.layers.25.self_attn.o_proj.weight": "model_layers_25_self_attn_o_proj_weight.safetensors",
    "model.layers.25.self_attn.q_proj.bias": "model_layers_25_self_attn_q_proj_bias.safetensors",
    "model.layers.25.self_attn.q_proj.weight": "model_layers_25_self_attn_q_proj_weight.safetensors",
    "model.layers.25.self_attn.v_proj.bias": "model_layers_25_self_attn_v_proj_bias.safetensors",
    "model.layers.25.self_attn.v_proj.weight": "model_layers_25_self_attn_v_proj_weight.safetensors",
    "model.layers.26.input_layernorm.weight": "model_layers_26_input_layernorm_weight.safetensors",
    "model.layers.26.mlp.down_proj.weight": "model_layers_26_mlp_down_proj_weight.safetensors",
    "model.layers.26.mlp.gate_proj.weight": "model_layers_26_mlp_gate_proj_weight.safetensors",
    "model.layers.26.mlp.up_proj.weight": "model_layers_26_mlp_up_proj_weight.safetensors",
    "model.layers.26.post_attention_layernorm.weight": "model_layers_26_post_attention_layernorm_weight.safetensors",
    "model.layers.26.self_attn.k_proj.bias": "model_layers_26_self_attn_k_proj_bias.safetensors",
    "model.layers.26.self_attn.k_proj.weight": "model_layers_26_self_attn_k_proj_weight.safetensors",
    "model.layers.26.self_attn.o_proj.weight": "model_layers_26_self_attn_o_proj_weight.safetensors",
    "model.layers.26.self_attn.q_proj.bias": "model_layers_26_self_attn_q_proj_bias.safetensors",
    "model.layers.26.self_attn.q_proj.weight": "model_layers_26_self_attn_q_proj_weight.safetensors",
    "model.layers.26.self_attn.v_proj.bias": "model_layers_26_self_attn_v_proj_bias.safetensors",
    "model.layers.26.self_attn.v_proj.weight": "model_layers_26_self_attn_v_proj_weight.safetensors",
    "model.layers.27.input_layernorm.weight": "model_layers_27_input_layernorm_weight.safetensors",
    "model.layers.27.mlp.down_proj.weight": "model_layers_27_mlp_down_proj_weight.safetensors",
    "model.layers.27.mlp.gate_proj.weight": "model_layers_27_mlp_gate_proj_weight.safetensors",
    "model.layers.27.mlp.up_proj.weight": "model_layers_27_mlp_up_proj_weight.safetensors",
    "model.layers.27.post_attention_layernorm.weight": "model_layers_27_post_attention_layernorm_weight.safetensors",
    "model.layers.27.self_attn.k_proj.bias": "model_layers_27_self_attn_k_proj_bias.safetensors",
    "model.layers.27.self_attn.k_proj.weight": "model_layers_27_self_attn_k_proj_weight.safetensors",
    "model.layers.27.self_attn.o_proj.weight": "model_layers_27_self_attn_o_proj_weight.safetensors",
    "model.layers.27.self_attn.q_proj.bias": "model_layers_27_self_attn_q_proj_bias.safetensors",
    "model.layers.27.self_attn.q_proj.weight": "model_layers_27_self_attn_q_proj_weight.safetensors",
    "model.layers.27.self_attn.v_proj.bias": "model_layers_27_self_attn_v_proj_bias.safetensors",
    "model.layers.27.self_attn.v_proj.weight": "model_layers_27_self_attn_v_proj_weight.safetensors",
    "model.layers.28.input_layernorm.weight": "model_layers_28_input_layernorm_weight.safetensors",
    "model.layers.28.mlp.down_proj.weight": "model_layers_28_mlp_down_proj_weight.safetensors",
    "model.layers.28.mlp.gate_proj.weight": "model_layers_28_mlp_gate_proj_weight.safetensors",
    "model.layers.28.mlp.up_proj.weight": "model_layers_28_mlp_up_proj_weight.safetensors",
    "model.layers.28.post_attention_layernorm.weight": "model_layers_28_post_attention_layernorm_weight.safetensors",
    "model.layers.28.self_attn.k_proj.bias": "model_layers_28_self_attn_k_proj_bias.safetensors",
    "model.layers.28.self_attn.k_proj.weight": "model_layers_28_self_attn_k_proj_weight.safetensors",
    "model.layers.28.self_attn.o_proj.weight": "model_layers_28_self_attn_o_proj_weight.safetensors",
    "model.layers.28.self_attn.q_proj.bias": "model_layers_28_self_attn_q_proj_bias.safetensors",
    "model.layers.28.self_attn.q_proj.weight": "model_layers_28_self_attn_q_proj_weight.safetensors",
    "model.layers.28.self_attn.v_proj.bias": "model_layers_28_self_attn_v_proj_bias.safetensors",
    "model.layers.28.self_attn.v_proj.weight": "model_layers_28_self_attn_v_proj_weight.safetensors",
    "model.layers.29.input_layernorm.weight": "model_layers_29_input_layernorm_weight.safetensors",
    "model.layers.29.mlp.down_proj.weight": "model_layers_29_mlp_down_proj_weight.safetensors",
    "model.layers.29.mlp.gate_proj.weight": "model_layers_29_mlp_gate_proj_weight.safetensors",
    "model.layers.29.mlp.up_proj.weight": "model_layers_29_mlp_up_proj_weight.safetensors",
    "model.layers.29.post_attention_layernorm.weight": "model_layers_29_post_attention_layernorm_weight.safetensors",
    "model.layers.29.self_attn.k_proj.bias": "model_layers_29_self_attn_k_proj_bias.safetensors",
    "model.layers.29.self_attn.k_proj.weight": "model_layers_29_self_attn_k_proj_weight.safetensors",
    "model.layers.29.self_attn.o_proj.weight": "model_layers_29_self_attn_o_proj_weight.safetensors",
    "model.layers.29.self_attn.q_proj.bias": "model_layers_29_self_attn_q_proj_bias.safetensors",
    "model.layers.29.self_attn.q_proj.weight": "model_layers_29_self_attn_q_proj_weight.safetensors",
    "model.layers.29.self_attn.v_proj.bias": "model_layers_29_self_attn_v_proj_bias.safetensors",
    "model.layers.29.self_attn.v_proj.weight": "model_layers_29_self_attn_v_proj_weight.safetensors",
    "model.layers.2.input_layernorm.weight": "model_layers_2_input_layernorm_weight.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model_layers_2_mlp_down_proj_weight.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "model_layers_2_mlp_gate_proj_weight.safetensors",
    "model.layers.2.mlp.up_proj.weight": "model_layers_2_mlp_up_proj_weight.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model_layers_2_post_attention_layernorm_weight.safetensors",
    "model.layers.2.self_attn.k_proj.bias": "model_layers_2_self_attn_k_proj_bias.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model_layers_2_self_attn_k_proj_weight.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model_layers_2_self_attn_o_proj_weight.safetensors",
    "model.layers.2.self_attn.q_proj.bias": "model_layers_2_self_attn_q_proj_bias.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model_layers_2_self_attn_q_proj_weight.safetensors",
    "model.layers.2.self_attn.v_proj.bias": "model_layers_2_self_attn_v_proj_bias.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model_layers_2_self_attn_v_proj_weight.safetensors",
    "model.layers.30.input_layernorm.weight": "model_layers_30_input_layernorm_weight.safetensors",
    "model.layers.30.mlp.down_proj.weight": "model_layers_30_mlp_down_proj_weight.safetensors",
    "model.layers.30.mlp.gate_proj.weight": "model_layers_30_mlp_gate_proj_weight.safetensors",
    "model.layers.30.mlp.up_proj.weight": "model_layers_30_mlp_up_proj_weight.safetensors",
    "model.layers.30.post_attention_layernorm.weight": "model_layers_30_post_attention_layernorm_weight.safetensors",
    "model.layers.30.self_attn.k_proj.bias": "model_layers_30_self_attn_k_proj_bias.safetensors",
    "model.layers.30.self_attn.k_proj.weight": "model_layers_30_self_attn_k_proj_weight.safetensors",
    "model.layers.30.self_attn.o_proj.weight": "model_layers_30_self_attn_o_proj_weight.safetensors",
    "model.layers.30.self_attn.q_proj.bias": "model_layers_30_self_attn_q_proj_bias.safetensors",
    "model.layers.30.self_attn.q_proj.weight": "model_layers_30_self_attn_q_proj_weight.safetensors",
    "model.layers.30.self_attn.v_proj.bias": "model_layers_30_self_attn_v_proj_bias.safetensors",
    "model.layers.30.self_attn.v_proj.weight": "model_layers_30_self_attn_v_proj_weight.safetensors",
    "model.layers.31.input_layernorm.weight": "model_layers_31_input_layernorm_weight.safetensors",
    "model.layers.31.mlp.down_proj.weight": "model_layers_31_mlp_down_proj_weight.safetensors",
    "model.layers.31.mlp.gate_proj.weight": "model_layers_31_mlp_gate_proj_weight.safetensors",
    "model.layers.31.mlp.up_proj.weight": "model_layers_31_mlp_up_proj_weight.safetensors",
    "model.layers.31.post_attention_layernorm.weight": "model_layers_31_post_attention_layernorm_weight.safetensors",
    "model.layers.31.self_attn.k_proj.bias": "model_layers_31_self_attn_k_proj_bias.safetensors",
    "model.layers.31.self_attn.k_proj.weight": "model_layers_31_self_attn_k_proj_weight.safetensors",
    "model.layers.31.self_attn.o_proj.weight": "model_layers_31_self_attn_o_proj_weight.safetensors",
    "model.layers.31.self_attn.q_proj.bias": "model_layers_31_self_attn_q_proj_bias.safetensors",
    "model.layers.31.self_attn.q_proj.weight": "model_layers_31_self_attn_q_proj_weight.safetensors",
    "model.layers.31.self_attn.v_proj.bias": "model_layers_31_self_attn_v_proj_bias.safetensors",
    "model.layers.31.self_attn.v_proj.weight": "model_layers_31_self_attn_v_proj_weight.safetensors",
    "model.layers.32.input_layernorm.weight": "model_layers_32_input_layernorm_weight.safetensors",
    "model.layers.32.mlp.down_proj.weight": "model_layers_32_mlp_down_proj_weight.safetensors",
    "model.layers.32.mlp.gate_proj.weight": "model_layers_32_mlp_gate_proj_weight.safetensors",
    "model.layers.32.mlp.up_proj.weight": "model_layers_32_mlp_up_proj_weight.safetensors",
    "model.layers.32.post_attention_layernorm.weight": "model_layers_32_post_attention_layernorm_weight.safetensors",
    "model.layers.32.self_attn.k_proj.bias": "model_layers_32_self_attn_k_proj_bias.safetensors",
    "model.layers.32.self_attn.k_proj.weight": "model_layers_32_self_attn_k_proj_weight.safetensors",
    "model.layers.32.self_attn.o_proj.weight": "model_layers_32_self_attn_o_proj_weight.safetensors",
    "model.layers.32.self_attn.q_proj.bias": "model_layers_32_self_attn_q_proj_bias.safetensors",
    "model.layers.32.self_attn.q_proj.weight": "model_layers_32_self_attn_q_proj_weight.safetensors",
    "model.layers.32.self_attn.v_proj.bias": "model_layers_32_self_attn_v_proj_bias.safetensors",
    "model.layers.32.self_attn.v_proj.weight": "model_layers_32_self_attn_v_proj_weight.safetensors",
    "model.layers.33.input_layernorm.weight": "model_layers_33_input_layernorm_weight.safetensors",
    "model.layers.33.mlp.down_proj.weight": "model_layers_33_mlp_down_proj_weight.safetensors",
    "model.layers.33.mlp.gate_proj.weight": "model_layers_33_mlp_gate_proj_weight.safetensors",
    "model.layers.33.mlp.up_proj.weight": "model_layers_33_mlp_up_proj_weight.safetensors",
    "model.layers.33.post_attention_layernorm.weight": "model_layers_33_post_attention_layernorm_weight.safetensors",
    "model.layers.33.self_attn.k_proj.bias": "model_layers_33_self_attn_k_proj_bias.safetensors",
    "model.layers.33.self_attn.k_proj.weight": "model_layers_33_self_attn_k_proj_weight.safetensors",
    "model.layers.33.self_attn.o_proj.weight": "model_layers_33_self_attn_o_proj_weight.safetensors",
    "model.layers.33.self_attn.q_proj.bias": "model_layers_33_self_attn_q_proj_bias.safetensors",
    "model.layers.33.self_attn.q_proj.weight": "model_layers_33_self_attn_q_proj_weight.safetensors",
    "model.layers.33.self_attn.v_proj.bias": "model_layers_33_self_attn_v_proj_bias.safetensors",
    "model.layers.33.self_attn.v_proj.weight": "model_layers_33_self_attn_v_proj_weight.safetensors",
    "model.layers.34.input_layernorm.weight": "model_layers_34_input_layernorm_weight.safetensors",
    "model.layers.34.mlp.down_proj.weight": "model_layers_34_mlp_down_proj_weight.safetensors",
    "model.layers.34.mlp.gate_proj.weight": "model_layers_34_mlp_gate_proj_weight.safetensors",
    "model.layers.34.mlp.up_proj.weight": "model_layers_34_mlp_up_proj_weight.safetensors",
    "model.layers.34.post_attention_layernorm.weight": "model_layers_34_post_attention_layernorm_weight.safetensors",
    "model.layers.34.self_attn.k_proj.bias": "model_layers_34_self_attn_k_proj_bias.safetensors",
    "model.layers.34.self_attn.k_proj.weight": "model_layers_34_self_attn_k_proj_weight.safetensors",
    "model.layers.34.self_attn.o_proj.weight": "model_layers_34_self_attn_o_proj_weight.safetensors",
    "model.layers.34.self_attn.q_proj.bias": "model_layers_34_self_attn_q_proj_bias.safetensors",
    "model.layers.34.self_attn.q_proj.weight": "model_layers_34_self_attn_q_proj_weight.safetensors",
    "model.layers.34.self_attn.v_proj.bias": "model_layers_34_self_attn_v_proj_bias.safetensors",
    "model.layers.34.self_attn.v_proj.weight": "model_layers_34_self_attn_v_proj_weight.safetensors",
    "model.layers.35.input_layernorm.weight": "model_layers_35_input_layernorm_weight.safetensors",
    "model.layers.35.mlp.down_proj.weight": "model_layers_35_mlp_down_proj_weight.safetensors",
    "model.layers.35.mlp.gate_proj.weight": "model_layers_35_mlp_gate_proj_weight.safetensors",
    "model.layers.35.mlp.up_proj.weight": "model_layers_35_mlp_up_proj_weight.safetensors",
    "model.layers.35.post_attention_layernorm.weight": "model_layers_35_post_attention_layernorm_weight.safetensors",
    "model.layers.35.self_attn.k_proj.bias": "model_layers_35_self_attn_k_proj_bias.safetensors",
    "model.layers.35.self_attn.k_proj.weight": "model_layers_35_self_attn_k_proj_weight.safetensors",
    "model.layers.35.self_attn.o_proj.weight": "model_layers_35_self_attn_o_proj_weight.safetensors",
    "model.layers.35.self_attn.q_proj.bias": "model_layers_35_self_attn_q_proj_bias.safetensors",
    "model.layers.35.self_attn.q_proj.weight": "model_layers_35_self_attn_q_proj_weight.safetensors",
    "model.layers.35.self_attn.v_proj.bias": "model_layers_35_self_attn_v_proj_bias.safetensors",
    "model.layers.35.self_attn.v_proj.weight": "model_layers_35_self_attn_v_proj_weight.safetensors",
    "model.layers.36.input_layernorm.weight": "model_layers_36_input_layernorm_weight.safetensors",
    "model.layers.36.mlp.down_proj.weight": "model_layers_36_mlp_down_proj_weight.safetensors",
    "model.layers.36.mlp.gate_proj.weight": "model_layers_36_mlp_gate_proj_weight.safetensors",
    "model.layers.36.mlp.up_proj.weight": "model_layers_36_mlp_up_proj_weight.safetensors",
    "model.layers.36.post_attention_layernorm.weight": "model_layers_36_post_attention_layernorm_weight.safetensors",
    "model.layers.36.self_attn.k_proj.bias": "model_layers_36_self_attn_k_proj_bias.safetensors",
    "model.layers.36.self_attn.k_proj.weight": "model_layers_36_self_attn_k_proj_weight.safetensors",
    "model.layers.36.self_attn.o_proj.weight": "model_layers_36_self_attn_o_proj_weight.safetensors",
    "model.layers.36.self_attn.q_proj.bias": "model_layers_36_self_attn_q_proj_bias.safetensors",
    "model.layers.36.self_attn.q_proj.weight": "model_layers_36_self_attn_q_proj_weight.safetensors",
    "model.layers.36.self_attn.v_proj.bias": "model_layers_36_self_attn_v_proj_bias.safetensors",
    "model.layers.36.self_attn.v_proj.weight": "model_layers_36_self_attn_v_proj_weight.safetensors",
    "model.layers.37.input_layernorm.weight": "model_layers_37_input_layernorm_weight.safetensors",
    "model.layers.37.mlp.down_proj.weight": "model_layers_37_mlp_down_proj_weight.safetensors",
    "model.layers.37.mlp.gate_proj.weight": "model_layers_37_mlp_gate_proj_weight.safetensors",
    "model.layers.37.mlp.up_proj.weight": "model_layers_37_mlp_up_proj_weight.safetensors",
    "model.layers.37.post_attention_layernorm.weight": "model_layers_37_post_attention_layernorm_weight.safetensors",
    "model.layers.37.self_attn.k_proj.bias": "model_layers_37_self_attn_k_proj_bias.safetensors",
    "model.layers.37.self_attn.k_proj.weight": "model_layers_37_self_attn_k_proj_weight.safetensors",
    "model.layers.37.self_attn.o_proj.weight": "model_layers_37_self_attn_o_proj_weight.safetensors",
    "model.layers.37.self_attn.q_proj.bias": "model_layers_37_self_attn_q_proj_bias.safetensors",
    "model.layers.37.self_attn.q_proj.weight": "model_layers_37_self_attn_q_proj_weight.safetensors",
    "model.layers.37.self_attn.v_proj.bias": "model_layers_37_self_attn_v_proj_bias.safetensors",
    "model.layers.37.self_attn.v_proj.weight": "model_layers_37_self_attn_v_proj_weight.safetensors",
    "model.layers.38.input_layernorm.weight": "model_layers_38_input_layernorm_weight.safetensors",
    "model.layers.38.mlp.down_proj.weight": "model_layers_38_mlp_down_proj_weight.safetensors",
    "model.layers.38.mlp.gate_proj.weight": "model_layers_38_mlp_gate_proj_weight.safetensors",
    "model.layers.38.mlp.up_proj.weight": "model_layers_38_mlp_up_proj_weight.safetensors",
    "model.layers.38.post_attention_layernorm.weight": "model_layers_38_post_attention_layernorm_weight.safetensors",
    "model.layers.38.self_attn.k_proj.bias": "model_layers_38_self_attn_k_proj_bias.safetensors",
    "model.layers.38.self_attn.k_proj.weight": "model_layers_38_self_attn_k_proj_weight.safetensors",
    "model.layers.38.self_attn.o_proj.weight": "model_layers_38_self_attn_o_proj_weight.safetensors",
    "model.layers.38.self_attn.q_proj.bias": "model_layers_38_self_attn_q_proj_bias.safetensors",
    "model.layers.38.self_attn.q_proj.weight": "model_layers_38_self_attn_q_proj_weight.safetensors",
    "model.layers.38.self_attn.v_proj.bias": "model_layers_38_self_attn_v_proj_bias.safetensors",
    "model.layers.38.self_attn.v_proj.weight": "model_layers_38_self_attn_v_proj_weight.safetensors",
    "model.layers.39.input_layernorm.weight": "model_layers_39_input_layernorm_weight.safetensors",
    "model.layers.39.mlp.down_proj.weight": "model_layers_39_mlp_down_proj_weight.safetensors",
    "model.layers.39.mlp.gate_proj.weight": "model_layers_39_mlp_gate_proj_weight.safetensors",
    "model.layers.39.mlp.up_proj.weight": "model_layers_39_mlp_up_proj_weight.safetensors",
    "model.layers.39.post_attention_layernorm.weight": "model_layers_39_post_attention_layernorm_weight.safetensors",
    "model.layers.39.self_attn.k_proj.bias": "model_layers_39_self_attn_k_proj_bias.safetensors",
    "model.layers.39.self_attn.k_proj.weight": "model_layers_39_self_attn_k_proj_weight.safetensors",
    "model.layers.39.self_attn.o_proj.weight": "model_layers_39_self_attn_o_proj_weight.safetensors",
    "model.layers.39.self_attn.q_proj.bias": "model_layers_39_self_attn_q_proj_bias.safetensors",
    "model.layers.39.self_attn.q_proj.weight": "model_layers_39_self_attn_q_proj_weight.safetensors",
    "model.layers.39.self_attn.v_proj.bias": "model_layers_39_self_attn_v_proj_bias.safetensors",
    "model.layers.39.self_attn.v_proj.weight": "model_layers_39_self_attn_v_proj_weight.safetensors",
    "model.layers.3.input_layernorm.weight": "model_layers_3_input_layernorm_weight.safetensors",
    "model.layers.3.mlp.down_proj.weight": "model_layers_3_mlp_down_proj_weight.safetensors",
    "model.layers.3.mlp.gate_proj.weight": "model_layers_3_mlp_gate_proj_weight.safetensors",
    "model.layers.3.mlp.up_proj.weight": "model_layers_3_mlp_up_proj_weight.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model_layers_3_post_attention_layernorm_weight.safetensors",
    "model.layers.3.self_attn.k_proj.bias": "model_layers_3_self_attn_k_proj_bias.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "model_layers_3_self_attn_k_proj_weight.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model_layers_3_self_attn_o_proj_weight.safetensors",
    "model.layers.3.self_attn.q_proj.bias": "model_layers_3_self_attn_q_proj_bias.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "model_layers_3_self_attn_q_proj_weight.safetensors",
    "model.layers.3.self_attn.v_proj.bias": "model_layers_3_self_attn_v_proj_bias.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "model_layers_3_self_attn_v_proj_weight.safetensors",
    "model.layers.40.input_layernorm.weight": "model_layers_40_input_layernorm_weight.safetensors",
    "model.layers.40.mlp.down_proj.weight": "model_layers_40_mlp_down_proj_weight.safetensors",
    "model.layers.40.mlp.gate_proj.weight": "model_layers_40_mlp_gate_proj_weight.safetensors",
    "model.layers.40.mlp.up_proj.weight": "model_layers_40_mlp_up_proj_weight.safetensors",
    "model.layers.40.post_attention_layernorm.weight": "model_layers_40_post_attention_layernorm_weight.safetensors",
    "model.layers.40.self_attn.k_proj.bias": "model_layers_40_self_attn_k_proj_bias.safetensors",
    "model.layers.40.self_attn.k_proj.weight": "model_layers_40_self_attn_k_proj_weight.safetensors",
    "model.layers.40.self_attn.o_proj.weight": "model_layers_40_self_attn_o_proj_weight.safetensors",
    "model.layers.40.self_attn.q_proj.bias": "model_layers_40_self_attn_q_proj_bias.safetensors",
    "model.layers.40.self_attn.q_proj.weight": "model_layers_40_self_attn_q_proj_weight.safetensors",
    "model.layers.40.self_attn.v_proj.bias": "model_layers_40_self_attn_v_proj_bias.safetensors",
    "model.layers.40.self_attn.v_proj.weight": "model_layers_40_self_attn_v_proj_weight.safetensors",
    "model.layers.41.input_layernorm.weight": "model_layers_41_input_layernorm_weight.safetensors",
    "model.layers.41.mlp.down_proj.weight": "model_layers_41_mlp_down_proj_weight.safetensors",
    "model.layers.41.mlp.gate_proj.weight": "model_layers_41_mlp_gate_proj_weight.safetensors",
    "model.layers.41.mlp.up_proj.weight": "model_layers_41_mlp_up_proj_weight.safetensors",
    "model.layers.41.post_attention_layernorm.weight": "model_layers_41_post_attention_layernorm_weight.safetensors",
    "model.layers.41.self_attn.k_proj.bias": "model_layers_41_self_attn_k_proj_bias.safetensors",
    "model.layers.41.self_attn.k_proj.weight": "model_layers_41_self_attn_k_proj_weight.safetensors",
    "model.layers.41.self_attn.o_proj.weight": "model_layers_41_self_attn_o_proj_weight.safetensors",
    "model.layers.41.self_attn.q_proj.bias": "model_layers_41_self_attn_q_proj_bias.safetensors",
    "model.layers.41.self_attn.q_proj.weight": "model_layers_41_self_attn_q_proj_weight.safetensors",
    "model.layers.41.self_attn.v_proj.bias": "model_layers_41_self_attn_v_proj_bias.safetensors",
    "model.layers.41.self_attn.v_proj.weight": "model_layers_41_self_attn_v_proj_weight.safetensors",
    "model.layers.42.input_layernorm.weight": "model_layers_42_input_layernorm_weight.safetensors",
    "model.layers.42.mlp.down_proj.weight": "model_layers_42_mlp_down_proj_weight.safetensors",
    "model.layers.42.mlp.gate_proj.weight": "model_layers_42_mlp_gate_proj_weight.safetensors",
    "model.layers.42.mlp.up_proj.weight": "model_layers_42_mlp_up_proj_weight.safetensors",
    "model.layers.42.post_attention_layernorm.weight": "model_layers_42_post_attention_layernorm_weight.safetensors",
    "model.layers.42.self_attn.k_proj.bias": "model_layers_42_self_attn_k_proj_bias.safetensors",
    "model.layers.42.self_attn.k_proj.weight": "model_layers_42_self_attn_k_proj_weight.safetensors",
    "model.layers.42.self_attn.o_proj.weight": "model_layers_42_self_attn_o_proj_weight.safetensors",
    "model.layers.42.self_attn.q_proj.bias": "model_layers_42_self_attn_q_proj_bias.safetensors",
    "model.layers.42.self_attn.q_proj.weight": "model_layers_42_self_attn_q_proj_weight.safetensors",
    "model.layers.42.self_attn.v_proj.bias": "model_layers_42_self_attn_v_proj_bias.safetensors",
    "model.layers.42.self_attn.v_proj.weight": "model_layers_42_self_attn_v_proj_weight.safetensors",
    "model.layers.43.input_layernorm.weight": "model_layers_43_input_layernorm_weight.safetensors",
    "model.layers.43.mlp.down_proj.weight": "model_layers_43_mlp_down_proj_weight.safetensors",
    "model.layers.43.mlp.gate_proj.weight": "model_layers_43_mlp_gate_proj_weight.safetensors",
    "model.layers.43.mlp.up_proj.weight": "model_layers_43_mlp_up_proj_weight.safetensors",
    "model.layers.43.post_attention_layernorm.weight": "model_layers_43_post_attention_layernorm_weight.safetensors",
    "model.layers.43.self_attn.k_proj.bias": "model_layers_43_self_attn_k_proj_bias.safetensors",
    "model.layers.43.self_attn.k_proj.weight": "model_layers_43_self_attn_k_proj_weight.safetensors",
    "model.layers.43.self_attn.o_proj.weight": "model_layers_43_self_attn_o_proj_weight.safetensors",
    "model.layers.43.self_attn.q_proj.bias": "model_layers_43_self_attn_q_proj_bias.safetensors",
    "model.layers.43.self_attn.q_proj.weight": "model_layers_43_self_attn_q_proj_weight.safetensors",
    "model.layers.43.self_attn.v_proj.bias": "model_layers_43_self_attn_v_proj_bias.safetensors",
    "model.layers.43.self_attn.v_proj.weight": "model_layers_43_self_attn_v_proj_weight.safetensors",
    "model.layers.44.input_layernorm.weight": "model_layers_44_input_layernorm_weight.safetensors",
    "model.layers.44.mlp.down_proj.weight": "model_layers_44_mlp_down_proj_weight.safetensors",
    "model.layers.44.mlp.gate_proj.weight": "model_layers_44_mlp_gate_proj_weight.safetensors",
    "model.layers.44.mlp.up_proj.weight": "model_layers_44_mlp_up_proj_weight.safetensors",
    "model.layers.44.post_attention_layernorm.weight": "model_layers_44_post_attention_layernorm_weight.safetensors",
    "model.layers.44.self_attn.k_proj.bias": "model_layers_44_self_attn_k_proj_bias.safetensors",
    "model.layers.44.self_attn.k_proj.weight": "model_layers_44_self_attn_k_proj_weight.safetensors",
    "model.layers.44.self_attn.o_proj.weight": "model_layers_44_self_attn_o_proj_weight.safetensors",
    "model.layers.44.self_attn.q_proj.bias": "model_layers_44_self_attn_q_proj_bias.safetensors",
    "model.layers.44.self_attn.q_proj.weight": "model_layers_44_self_attn_q_proj_weight.safetensors",
    "model.layers.44.self_attn.v_proj.bias": "model_layers_44_self_attn_v_proj_bias.safetensors",
    "model.layers.44.self_attn.v_proj.weight": "model_layers_44_self_attn_v_proj_weight.safetensors",
    "model.layers.45.input_layernorm.weight": "model_layers_45_input_layernorm_weight.safetensors",
    "model.layers.45.mlp.down_proj.weight": "model_layers_45_mlp_down_proj_weight.safetensors",
    "model.layers.45.mlp.gate_proj.weight": "model_layers_45_mlp_gate_proj_weight.safetensors",
    "model.layers.45.mlp.up_proj.weight": "model_layers_45_mlp_up_proj_weight.safetensors",
    "model.layers.45.post_attention_layernorm.weight": "model_layers_45_post_attention_layernorm_weight.safetensors",
    "model.layers.45.self_attn.k_proj.bias": "model_layers_45_self_attn_k_proj_bias.safetensors",
    "model.layers.45.self_attn.k_proj.weight": "model_layers_45_self_attn_k_proj_weight.safetensors",
    "model.layers.45.self_attn.o_proj.weight": "model_layers_45_self_attn_o_proj_weight.safetensors",
    "model.layers.45.self_attn.q_proj.bias": "model_layers_45_self_attn_q_proj_bias.safetensors",
    "model.layers.45.self_attn.q_proj.weight": "model_layers_45_self_attn_q_proj_weight.safetensors",
    "model.layers.45.self_attn.v_proj.bias": "model_layers_45_self_attn_v_proj_bias.safetensors",
    "model.layers.45.self_attn.v_proj.weight": "model_layers_45_self_attn_v_proj_weight.safetensors",
    "model.layers.46.input_layernorm.weight": "model_layers_46_input_layernorm_weight.safetensors",
    "model.layers.46.mlp.down_proj.weight": "model_layers_46_mlp_down_proj_weight.safetensors",
    "model.layers.46.mlp.gate_proj.weight": "model_layers_46_mlp_gate_proj_weight.safetensors",
    "model.layers.46.mlp.up_proj.weight": "model_layers_46_mlp_up_proj_weight.safetensors",
    "model.layers.46.post_attention_layernorm.weight": "model_layers_46_post_attention_layernorm_weight.safetensors",
    "model.layers.46.self_attn.k_proj.bias": "model_layers_46_self_attn_k_proj_bias.safetensors",
    "model.layers.46.self_attn.k_proj.weight": "model_layers_46_self_attn_k_proj_weight.safetensors",
    "model.layers.46.self_attn.o_proj.weight": "model_layers_46_self_attn_o_proj_weight.safetensors",
    "model.layers.46.self_attn.q_proj.bias": "model_layers_46_self_attn_q_proj_bias.safetensors",
    "model.layers.46.self_attn.q_proj.weight": "model_layers_46_self_attn_q_proj_weight.safetensors",
    "model.layers.46.self_attn.v_proj.bias": "model_layers_46_self_attn_v_proj_bias.safetensors",
    "model.layers.46.self_attn.v_proj.weight": "model_layers_46_self_attn_v_proj_weight.safetensors",
    "model.layers.47.input_layernorm.weight": "model_layers_47_input_layernorm_weight.safetensors",
    "model.layers.47.mlp.down_proj.weight": "model_layers_47_mlp_down_proj_weight.safetensors",
    "model.layers.47.mlp.gate_proj.weight": "model_layers_47_mlp_gate_proj_weight.safetensors",
    "model.layers.47.mlp.up_proj.weight": "model_layers_47_mlp_up_proj_weight.safetensors",
    "model.layers.47.post_attention_layernorm.weight": "model_layers_47_post_attention_layernorm_weight.safetensors",
    "model.layers.47.self_attn.k_proj.bias": "model_layers_47_self_attn_k_proj_bias.safetensors",
    "model.layers.47.self_attn.k_proj.weight": "model_layers_47_self_attn_k_proj_weight.safetensors",
    "model.layers.47.self_attn.o_proj.weight": "model_layers_47_self_attn_o_proj_weight.safetensors",
    "model.layers.47.self_attn.q_proj.bias": "model_layers_47_self_attn_q_proj_bias.safetensors",
    "model.layers.47.self_attn.q_proj.weight": "model_layers_47_self_attn_q_proj_weight.safetensors",
    "model.layers.47.self_attn.v_proj.bias": "model_layers_47_self_attn_v_proj_bias.safetensors",
    "model.layers.47.self_attn.v_proj.weight": "model_layers_47_self_attn_v_proj_weight.safetensors",
    "model.layers.48.input_layernorm.weight": "model_layers_48_input_layernorm_weight.safetensors",
    "model.layers.48.mlp.down_proj.weight": "model_layers_48_mlp_down_proj_weight.safetensors",
    "model.layers.48.mlp.gate_proj.weight": "model_layers_48_mlp_gate_proj_weight.safetensors",
    "model.layers.48.mlp.up_proj.weight": "model_layers_48_mlp_up_proj_weight.safetensors",
    "model.layers.48.post_attention_layernorm.weight": "model_layers_48_post_attention_layernorm_weight.safetensors",
    "model.layers.48.self_attn.k_proj.bias": "model_layers_48_self_attn_k_proj_bias.safetensors",
    "model.layers.48.self_attn.k_proj.weight": "model_layers_48_self_attn_k_proj_weight.safetensors",
    "model.layers.48.self_attn.o_proj.weight": "model_layers_48_self_attn_o_proj_weight.safetensors",
    "model.layers.48.self_attn.q_proj.bias": "model_layers_48_self_attn_q_proj_bias.safetensors",
    "model.layers.48.self_attn.q_proj.weight": "model_layers_48_self_attn_q_proj_weight.safetensors",
    "model.layers.48.self_attn.v_proj.bias": "model_layers_48_self_attn_v_proj_bias.safetensors",
    "model.layers.48.self_attn.v_proj.weight": "model_layers_48_self_attn_v_proj_weight.safetensors",
    "model.layers.49.input_layernorm.weight": "model_layers_49_input_layernorm_weight.safetensors",
    "model.layers.49.mlp.down_proj.weight": "model_layers_49_mlp_down_proj_weight.safetensors",
    "model.layers.49.mlp.gate_proj.weight": "model_layers_49_mlp_gate_proj_weight.safetensors",
    "model.layers.49.mlp.up_proj.weight": "model_layers_49_mlp_up_proj_weight.safetensors",
    "model.layers.49.post_attention_layernorm.weight": "model_layers_49_post_attention_layernorm_weight.safetensors",
    "model.layers.49.self_attn.k_proj.bias": "model_layers_49_self_attn_k_proj_bias.safetensors",
    "model.layers.49.self_attn.k_proj.weight": "model_layers_49_self_attn_k_proj_weight.safetensors",
    "model.layers.49.self_attn.o_proj.weight": "model_layers_49_self_attn_o_proj_weight.safetensors",
    "model.layers.49.self_attn.q_proj.bias": "model_layers_49_self_attn_q_proj_bias.safetensors",
    "model.layers.49.self_attn.q_proj.weight": "model_layers_49_self_attn_q_proj_weight.safetensors",
    "model.layers.49.self_attn.v_proj.bias": "model_layers_49_self_attn_v_proj_bias.safetensors",
    "model.layers.49.self_attn.v_proj.weight": "model_layers_49_self_attn_v_proj_weight.safetensors",
    "model.layers.4.input_layernorm.weight": "model_layers_4_input_layernorm_weight.safetensors",
    "model.layers.4.mlp.down_proj.weight": "model_layers_4_mlp_down_proj_weight.safetensors",
    "model.layers.4.mlp.gate_proj.weight": "model_layers_4_mlp_gate_proj_weight.safetensors",
    "model.layers.4.mlp.up_proj.weight": "model_layers_4_mlp_up_proj_weight.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model_layers_4_post_attention_layernorm_weight.safetensors",
    "model.layers.4.self_attn.k_proj.bias": "model_layers_4_self_attn_k_proj_bias.safetensors",
    "model.layers.4.self_attn.k_proj.weight": "model_layers_4_self_attn_k_proj_weight.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model_layers_4_self_attn_o_proj_weight.safetensors",
    "model.layers.4.self_attn.q_proj.bias": "model_layers_4_self_attn_q_proj_bias.safetensors",
    "model.layers.4.self_attn.q_proj.weight": "model_layers_4_self_attn_q_proj_weight.safetensors",
    "model.layers.4.self_attn.v_proj.bias": "model_layers_4_self_attn_v_proj_bias.safetensors",
    "model.layers.4.self_attn.v_proj.weight": "model_layers_4_self_attn_v_proj_weight.safetensors",
    "model.layers.50.input_layernorm.weight": "model_layers_50_input_layernorm_weight.safetensors",
    "model.layers.50.mlp.down_proj.weight": "model_layers_50_mlp_down_proj_weight.safetensors",
    "model.layers.50.mlp.gate_proj.weight": "model_layers_50_mlp_gate_proj_weight.safetensors",
    "model.layers.50.mlp.up_proj.weight": "model_layers_50_mlp_up_proj_weight.safetensors",
    "model.layers.50.post_attention_layernorm.weight": "model_layers_50_post_attention_layernorm_weight.safetensors",
    "model.layers.50.self_attn.k_proj.bias": "model_layers_50_self_attn_k_proj_bias.safetensors",
    "model.layers.50.self_attn.k_proj.weight": "model_layers_50_self_attn_k_proj_weight.safetensors",
    "model.layers.50.self_attn.o_proj.weight": "model_layers_50_self_attn_o_proj_weight.safetensors",
    "model.layers.50.self_attn.q_proj.bias": "model_layers_50_self_attn_q_proj_bias.safetensors",
    "model.layers.50.self_attn.q_proj.weight": "model_layers_50_self_attn_q_proj_weight.safetensors",
    "model.layers.50.self_attn.v_proj.bias": "model_layers_50_self_attn_v_proj_bias.safetensors",
    "model.layers.50.self_attn.v_proj.weight": "model_layers_50_self_attn_v_proj_weight.safetensors",
    "model.layers.51.input_layernorm.weight": "model_layers_51_input_layernorm_weight.safetensors",
    "model.layers.51.mlp.down_proj.weight": "model_layers_51_mlp_down_proj_weight.safetensors",
    "model.layers.51.mlp.gate_proj.weight": "model_layers_51_mlp_gate_proj_weight.safetensors",
    "model.layers.51.mlp.up_proj.weight": "model_layers_51_mlp_up_proj_weight.safetensors",
    "model.layers.51.post_attention_layernorm.weight": "model_layers_51_post_attention_layernorm_weight.safetensors",
    "model.layers.51.self_attn.k_proj.bias": "model_layers_51_self_attn_k_proj_bias.safetensors",
    "model.layers.51.self_attn.k_proj.weight": "model_layers_51_self_attn_k_proj_weight.safetensors",
    "model.layers.51.self_attn.o_proj.weight": "model_layers_51_self_attn_o_proj_weight.safetensors",
    "model.layers.51.self_attn.q_proj.bias": "model_layers_51_self_attn_q_proj_bias.safetensors",
    "model.layers.51.self_attn.q_proj.weight": "model_layers_51_self_attn_q_proj_weight.safetensors",
    "model.layers.51.self_attn.v_proj.bias": "model_layers_51_self_attn_v_proj_bias.safetensors",
    "model.layers.51.self_attn.v_proj.weight": "model_layers_51_self_attn_v_proj_weight.safetensors",
    "model.layers.52.input_layernorm.weight": "model_layers_52_input_layernorm_weight.safetensors",
    "model.layers.52.mlp.down_proj.weight": "model_layers_52_mlp_down_proj_weight.safetensors",
    "model.layers.52.mlp.gate_proj.weight": "model_layers_52_mlp_gate_proj_weight.safetensors",
    "model.layers.52.mlp.up_proj.weight": "model_layers_52_mlp_up_proj_weight.safetensors",
    "model.layers.52.post_attention_layernorm.weight": "model_layers_52_post_attention_layernorm_weight.safetensors",
    "model.layers.52.self_attn.k_proj.bias": "model_layers_52_self_attn_k_proj_bias.safetensors",
    "model.layers.52.self_attn.k_proj.weight": "model_layers_52_self_attn_k_proj_weight.safetensors",
    "model.layers.52.self_attn.o_proj.weight": "model_layers_52_self_attn_o_proj_weight.safetensors",
    "model.layers.52.self_attn.q_proj.bias": "model_layers_52_self_attn_q_proj_bias.safetensors",
    "model.layers.52.self_attn.q_proj.weight": "model_layers_52_self_attn_q_proj_weight.safetensors",
    "model.layers.52.self_attn.v_proj.bias": "model_layers_52_self_attn_v_proj_bias.safetensors",
    "model.layers.52.self_attn.v_proj.weight": "model_layers_52_self_attn_v_proj_weight.safetensors",
    "model.layers.53.input_layernorm.weight": "model_layers_53_input_layernorm_weight.safetensors",
    "model.layers.53.mlp.down_proj.weight": "model_layers_53_mlp_down_proj_weight.safetensors",
    "model.layers.53.mlp.gate_proj.weight": "model_layers_53_mlp_gate_proj_weight.safetensors",
    "model.layers.53.mlp.up_proj.weight": "model_layers_53_mlp_up_proj_weight.safetensors",
    "model.layers.53.post_attention_layernorm.weight": "model_layers_53_post_attention_layernorm_weight.safetensors",
    "model.layers.53.self_attn.k_proj.bias": "model_layers_53_self_attn_k_proj_bias.safetensors",
    "model.layers.53.self_attn.k_proj.weight": "model_layers_53_self_attn_k_proj_weight.safetensors",
    "model.layers.53.self_attn.o_proj.weight": "model_layers_53_self_attn_o_proj_weight.safetensors",
    "model.layers.53.self_attn.q_proj.bias": "model_layers_53_self_attn_q_proj_bias.safetensors",
    "model.layers.53.self_attn.q_proj.weight": "model_layers_53_self_attn_q_proj_weight.safetensors",
    "model.layers.53.self_attn.v_proj.bias": "model_layers_53_self_attn_v_proj_bias.safetensors",
    "model.layers.53.self_attn.v_proj.weight": "model_layers_53_self_attn_v_proj_weight.safetensors",
    "model.layers.54.input_layernorm.weight": "model_layers_54_input_layernorm_weight.safetensors",
    "model.layers.54.mlp.down_proj.weight": "model_layers_54_mlp_down_proj_weight.safetensors",
    "model.layers.54.mlp.gate_proj.weight": "model_layers_54_mlp_gate_proj_weight.safetensors",
    "model.layers.54.mlp.up_proj.weight": "model_layers_54_mlp_up_proj_weight.safetensors",
    "model.layers.54.post_attention_layernorm.weight": "model_layers_54_post_attention_layernorm_weight.safetensors",
    "model.layers.54.self_attn.k_proj.bias": "model_layers_54_self_attn_k_proj_bias.safetensors",
    "model.layers.54.self_attn.k_proj.weight": "model_layers_54_self_attn_k_proj_weight.safetensors",
    "model.layers.54.self_attn.o_proj.weight": "model_layers_54_self_attn_o_proj_weight.safetensors",
    "model.layers.54.self_attn.q_proj.bias": "model_layers_54_self_attn_q_proj_bias.safetensors",
    "model.layers.54.self_attn.q_proj.weight": "model_layers_54_self_attn_q_proj_weight.safetensors",
    "model.layers.54.self_attn.v_proj.bias": "model_layers_54_self_attn_v_proj_bias.safetensors",
    "model.layers.54.self_attn.v_proj.weight": "model_layers_54_self_attn_v_proj_weight.safetensors",
    "model.layers.55.input_layernorm.weight": "model_layers_55_input_layernorm_weight.safetensors",
    "model.layers.55.mlp.down_proj.weight": "model_layers_55_mlp_down_proj_weight.safetensors",
    "model.layers.55.mlp.gate_proj.weight": "model_layers_55_mlp_gate_proj_weight.safetensors",
    "model.layers.55.mlp.up_proj.weight": "model_layers_55_mlp_up_proj_weight.safetensors",
    "model.layers.55.post_attention_layernorm.weight": "model_layers_55_post_attention_layernorm_weight.safetensors",
    "model.layers.55.self_attn.k_proj.bias": "model_layers_55_self_attn_k_proj_bias.safetensors",
    "model.layers.55.self_attn.k_proj.weight": "model_layers_55_self_attn_k_proj_weight.safetensors",
    "model.layers.55.self_attn.o_proj.weight": "model_layers_55_self_attn_o_proj_weight.safetensors",
    "model.layers.55.self_attn.q_proj.bias": "model_layers_55_self_attn_q_proj_bias.safetensors",
    "model.layers.55.self_attn.q_proj.weight": "model_layers_55_self_attn_q_proj_weight.safetensors",
    "model.layers.55.self_attn.v_proj.bias": "model_layers_55_self_attn_v_proj_bias.safetensors",
    "model.layers.55.self_attn.v_proj.weight": "model_layers_55_self_attn_v_proj_weight.safetensors",
    "model.layers.56.input_layernorm.weight": "model_layers_56_input_layernorm_weight.safetensors",
    "model.layers.56.mlp.down_proj.weight": "model_layers_56_mlp_down_proj_weight.safetensors",
    "model.layers.56.mlp.gate_proj.weight": "model_layers_56_mlp_gate_proj_weight.safetensors",
    "model.layers.56.mlp.up_proj.weight": "model_layers_56_mlp_up_proj_weight.safetensors",
    "model.layers.56.post_attention_layernorm.weight": "model_layers_56_post_attention_layernorm_weight.safetensors",
    "model.layers.56.self_attn.k_proj.bias": "model_layers_56_self_attn_k_proj_bias.safetensors",
    "model.layers.56.self_attn.k_proj.weight": "model_layers_56_self_attn_k_proj_weight.safetensors",
    "model.layers.56.self_attn.o_proj.weight": "model_layers_56_self_attn_o_proj_weight.safetensors",
    "model.layers.56.self_attn.q_proj.bias": "model_layers_56_self_attn_q_proj_bias.safetensors",
    "model.layers.56.self_attn.q_proj.weight": "model_layers_56_self_attn_q_proj_weight.safetensors",
    "model.layers.56.self_attn.v_proj.bias": "model_layers_56_self_attn_v_proj_bias.safetensors",
    "model.layers.56.self_attn.v_proj.weight": "model_layers_56_self_attn_v_proj_weight.safetensors",
    "model.layers.57.input_layernorm.weight": "model_layers_57_input_layernorm_weight.safetensors",
    "model.layers.57.mlp.down_proj.weight": "model_layers_57_mlp_down_proj_weight.safetensors",
    "model.layers.57.mlp.gate_proj.weight": "model_layers_57_mlp_gate_proj_weight.safetensors",
    "model.layers.57.mlp.up_proj.weight": "model_layers_57_mlp_up_proj_weight.safetensors",
    "model.layers.57.post_attention_layernorm.weight": "model_layers_57_post_attention_layernorm_weight.safetensors",
    "model.layers.57.self_attn.k_proj.bias": "model_layers_57_self_attn_k_proj_bias.safetensors",
    "model.layers.57.self_attn.k_proj.weight": "model_layers_57_self_attn_k_proj_weight.safetensors",
    "model.layers.57.self_attn.o_proj.weight": "model_layers_57_self_attn_o_proj_weight.safetensors",
    "model.layers.57.self_attn.q_proj.bias": "model_layers_57_self_attn_q_proj_bias.safetensors",
    "model.layers.57.self_attn.q_proj.weight": "model_layers_57_self_attn_q_proj_weight.safetensors",
    "model.layers.57.self_attn.v_proj.bias": "model_layers_57_self_attn_v_proj_bias.safetensors",
    "model.layers.57.self_attn.v_proj.weight": "model_layers_57_self_attn_v_proj_weight.safetensors",
    "model.layers.58.input_layernorm.weight": "model_layers_58_input_layernorm_weight.safetensors",
    "model.layers.58.mlp.down_proj.weight": "model_layers_58_mlp_down_proj_weight.safetensors",
    "model.layers.58.mlp.gate_proj.weight": "model_layers_58_mlp_gate_proj_weight.safetensors",
    "model.layers.58.mlp.up_proj.weight": "model_layers_58_mlp_up_proj_weight.safetensors",
    "model.layers.58.post_attention_layernorm.weight": "model_layers_58_post_attention_layernorm_weight.safetensors",
    "model.layers.58.self_attn.k_proj.bias": "model_layers_58_self_attn_k_proj_bias.safetensors",
    "model.layers.58.self_attn.k_proj.weight": "model_layers_58_self_attn_k_proj_weight.safetensors",
    "model.layers.58.self_attn.o_proj.weight": "model_layers_58_self_attn_o_proj_weight.safetensors",
    "model.layers.58.self_attn.q_proj.bias": "model_layers_58_self_attn_q_proj_bias.safetensors",
    "model.layers.58.self_attn.q_proj.weight": "model_layers_58_self_attn_q_proj_weight.safetensors",
    "model.layers.58.self_attn.v_proj.bias": "model_layers_58_self_attn_v_proj_bias.safetensors",
    "model.layers.58.self_attn.v_proj.weight": "model_layers_58_self_attn_v_proj_weight.safetensors",
    "model.layers.59.input_layernorm.weight": "model_layers_59_input_layernorm_weight.safetensors",
    "model.layers.59.mlp.down_proj.weight": "model_layers_59_mlp_down_proj_weight.safetensors",
    "model.layers.59.mlp.gate_proj.weight": "model_layers_59_mlp_gate_proj_weight.safetensors",
    "model.layers.59.mlp.up_proj.weight": "model_layers_59_mlp_up_proj_weight.safetensors",
    "model.layers.59.post_attention_layernorm.weight": "model_layers_59_post_attention_layernorm_weight.safetensors",
    "model.layers.59.self_attn.k_proj.bias": "model_layers_59_self_attn_k_proj_bias.safetensors",
    "model.layers.59.self_attn.k_proj.weight": "model_layers_59_self_attn_k_proj_weight.safetensors",
    "model.layers.59.self_attn.o_proj.weight": "model_layers_59_self_attn_o_proj_weight.safetensors",
    "model.layers.59.self_attn.q_proj.bias": "model_layers_59_self_attn_q_proj_bias.safetensors",
    "model.layers.59.self_attn.q_proj.weight": "model_layers_59_self_attn_q_proj_weight.safetensors",
    "model.layers.59.self_attn.v_proj.bias": "model_layers_59_self_attn_v_proj_bias.safetensors",
    "model.layers.59.self_attn.v_proj.weight": "model_layers_59_self_attn_v_proj_weight.safetensors",
    "model.layers.5.input_layernorm.weight": "model_layers_5_input_layernorm_weight.safetensors",
    "model.layers.5.mlp.down_proj.weight": "model_layers_5_mlp_down_proj_weight.safetensors",
    "model.layers.5.mlp.gate_proj.weight": "model_layers_5_mlp_gate_proj_weight.safetensors",
    "model.layers.5.mlp.up_proj.weight": "model_layers_5_mlp_up_proj_weight.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model_layers_5_post_attention_layernorm_weight.safetensors",
    "model.layers.5.self_attn.k_proj.bias": "model_layers_5_self_attn_k_proj_bias.safetensors",
    "model.layers.5.self_attn.k_proj.weight": "model_layers_5_self_attn_k_proj_weight.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model_layers_5_self_attn_o_proj_weight.safetensors",
    "model.layers.5.self_attn.q_proj.bias": "model_layers_5_self_attn_q_proj_bias.safetensors",
    "model.layers.5.self_attn.q_proj.weight": "model_layers_5_self_attn_q_proj_weight.safetensors",
    "model.layers.5.self_attn.v_proj.bias": "model_layers_5_self_attn_v_proj_bias.safetensors",
    "model.layers.5.self_attn.v_proj.weight": "model_layers_5_self_attn_v_proj_weight.safetensors",
    "model.layers.60.input_layernorm.weight": "model_layers_60_input_layernorm_weight.safetensors",
    "model.layers.60.mlp.down_proj.weight": "model_layers_60_mlp_down_proj_weight.safetensors",
    "model.layers.60.mlp.gate_proj.weight": "model_layers_60_mlp_gate_proj_weight.safetensors",
    "model.layers.60.mlp.up_proj.weight": "model_layers_60_mlp_up_proj_weight.safetensors",
    "model.layers.60.post_attention_layernorm.weight": "model_layers_60_post_attention_layernorm_weight.safetensors",
    "model.layers.60.self_attn.k_proj.bias": "model_layers_60_self_attn_k_proj_bias.safetensors",
    "model.layers.60.self_attn.k_proj.weight": "model_layers_60_self_attn_k_proj_weight.safetensors",
    "model.layers.60.self_attn.o_proj.weight": "model_layers_60_self_attn_o_proj_weight.safetensors",
    "model.layers.60.self_attn.q_proj.bias": "model_layers_60_self_attn_q_proj_bias.safetensors",
    "model.layers.60.self_attn.q_proj.weight": "model_layers_60_self_attn_q_proj_weight.safetensors",
    "model.layers.60.self_attn.v_proj.bias": "model_layers_60_self_attn_v_proj_bias.safetensors",
    "model.layers.60.self_attn.v_proj.weight": "model_layers_60_self_attn_v_proj_weight.safetensors",
    "model.layers.61.input_layernorm.weight": "model_layers_61_input_layernorm_weight.safetensors",
    "model.layers.61.mlp.down_proj.weight": "model_layers_61_mlp_down_proj_weight.safetensors",
    "model.layers.61.mlp.gate_proj.weight": "model_layers_61_mlp_gate_proj_weight.safetensors",
    "model.layers.61.mlp.up_proj.weight": "model_layers_61_mlp_up_proj_weight.safetensors",
    "model.layers.61.post_attention_layernorm.weight": "model_layers_61_post_attention_layernorm_weight.safetensors",
    "model.layers.61.self_attn.k_proj.bias": "model_layers_61_self_attn_k_proj_bias.safetensors",
    "model.layers.61.self_attn.k_proj.weight": "model_layers_61_self_attn_k_proj_weight.safetensors",
    "model.layers.61.self_attn.o_proj.weight": "model_layers_61_self_attn_o_proj_weight.safetensors",
    "model.layers.61.self_attn.q_proj.bias": "model_layers_61_self_attn_q_proj_bias.safetensors",
    "model.layers.61.self_attn.q_proj.weight": "model_layers_61_self_attn_q_proj_weight.safetensors",
    "model.layers.61.self_attn.v_proj.bias": "model_layers_61_self_attn_v_proj_bias.safetensors",
    "model.layers.61.self_attn.v_proj.weight": "model_layers_61_self_attn_v_proj_weight.safetensors",
    "model.layers.62.input_layernorm.weight": "model_layers_62_input_layernorm_weight.safetensors",
    "model.layers.62.mlp.down_proj.weight": "model_layers_62_mlp_down_proj_weight.safetensors",
    "model.layers.62.mlp.gate_proj.weight": "model_layers_62_mlp_gate_proj_weight.safetensors",
    "model.layers.62.mlp.up_proj.weight": "model_layers_62_mlp_up_proj_weight.safetensors",
    "model.layers.62.post_attention_layernorm.weight": "model_layers_62_post_attention_layernorm_weight.safetensors",
    "model.layers.62.self_attn.k_proj.bias": "model_layers_62_self_attn_k_proj_bias.safetensors",
    "model.layers.62.self_attn.k_proj.weight": "model_layers_62_self_attn_k_proj_weight.safetensors",
    "model.layers.62.self_attn.o_proj.weight": "model_layers_62_self_attn_o_proj_weight.safetensors",
    "model.layers.62.self_attn.q_proj.bias": "model_layers_62_self_attn_q_proj_bias.safetensors",
    "model.layers.62.self_attn.q_proj.weight": "model_layers_62_self_attn_q_proj_weight.safetensors",
    "model.layers.62.self_attn.v_proj.bias": "model_layers_62_self_attn_v_proj_bias.safetensors",
    "model.layers.62.self_attn.v_proj.weight": "model_layers_62_self_attn_v_proj_weight.safetensors",
    "model.layers.63.input_layernorm.weight": "model_layers_63_input_layernorm_weight.safetensors",
    "model.layers.63.mlp.down_proj.weight": "model_layers_63_mlp_down_proj_weight.safetensors",
    "model.layers.63.mlp.gate_proj.weight": "model_layers_63_mlp_gate_proj_weight.safetensors",
    "model.layers.63.mlp.up_proj.weight": "model_layers_63_mlp_up_proj_weight.safetensors",
    "model.layers.63.post_attention_layernorm.weight": "model_layers_63_post_attention_layernorm_weight.safetensors",
    "model.layers.63.self_attn.k_proj.bias": "model_layers_63_self_attn_k_proj_bias.safetensors",
    "model.layers.63.self_attn.k_proj.weight": "model_layers_63_self_attn_k_proj_weight.safetensors",
    "model.layers.63.self_attn.o_proj.weight": "model_layers_63_self_attn_o_proj_weight.safetensors",
    "model.layers.63.self_attn.q_proj.bias": "model_layers_63_self_attn_q_proj_bias.safetensors",
    "model.layers.63.self_attn.q_proj.weight": "model_layers_63_self_attn_q_proj_weight.safetensors",
    "model.layers.63.self_attn.v_proj.bias": "model_layers_63_self_attn_v_proj_bias.safetensors",
    "model.layers.63.self_attn.v_proj.weight": "model_layers_63_self_attn_v_proj_weight.safetensors",
    "model.layers.64.input_layernorm.weight": "model_layers_64_input_layernorm_weight.safetensors",
    "model.layers.64.mlp.down_proj.weight": "model_layers_64_mlp_down_proj_weight.safetensors",
    "model.layers.64.mlp.gate_proj.weight": "model_layers_64_mlp_gate_proj_weight.safetensors",
    "model.layers.64.mlp.up_proj.weight": "model_layers_64_mlp_up_proj_weight.safetensors",
    "model.layers.64.post_attention_layernorm.weight": "model_layers_64_post_attention_layernorm_weight.safetensors",
    "model.layers.64.self_attn.k_proj.bias": "model_layers_64_self_attn_k_proj_bias.safetensors",
    "model.layers.64.self_attn.k_proj.weight": "model_layers_64_self_attn_k_proj_weight.safetensors",
    "model.layers.64.self_attn.o_proj.weight": "model_layers_64_self_attn_o_proj_weight.safetensors",
    "model.layers.64.self_attn.q_proj.bias": "model_layers_64_self_attn_q_proj_bias.safetensors",
    "model.layers.64.self_attn.q_proj.weight": "model_layers_64_self_attn_q_proj_weight.safetensors",
    "model.layers.64.self_attn.v_proj.bias": "model_layers_64_self_attn_v_proj_bias.safetensors",
    "model.layers.64.self_attn.v_proj.weight": "model_layers_64_self_attn_v_proj_weight.safetensors",
    "model.layers.65.input_layernorm.weight": "model_layers_65_input_layernorm_weight.safetensors",
    "model.layers.65.mlp.down_proj.weight": "model_layers_65_mlp_down_proj_weight.safetensors",
    "model.layers.65.mlp.gate_proj.weight": "model_layers_65_mlp_gate_proj_weight.safetensors",
    "model.layers.65.mlp.up_proj.weight": "model_layers_65_mlp_up_proj_weight.safetensors",
    "model.layers.65.post_attention_layernorm.weight": "model_layers_65_post_attention_layernorm_weight.safetensors",
    "model.layers.65.self_attn.k_proj.bias": "model_layers_65_self_attn_k_proj_bias.safetensors",
    "model.layers.65.self_attn.k_proj.weight": "model_layers_65_self_attn_k_proj_weight.safetensors",
    "model.layers.65.self_attn.o_proj.weight": "model_layers_65_self_attn_o_proj_weight.safetensors",
    "model.layers.65.self_attn.q_proj.bias": "model_layers_65_self_attn_q_proj_bias.safetensors",
    "model.layers.65.self_attn.q_proj.weight": "model_layers_65_self_attn_q_proj_weight.safetensors",
    "model.layers.65.self_attn.v_proj.bias": "model_layers_65_self_attn_v_proj_bias.safetensors",
    "model.layers.65.self_attn.v_proj.weight": "model_layers_65_self_attn_v_proj_weight.safetensors",
    "model.layers.66.input_layernorm.weight": "model_layers_66_input_layernorm_weight.safetensors",
    "model.layers.66.mlp.down_proj.weight": "model_layers_66_mlp_down_proj_weight.safetensors",
    "model.layers.66.mlp.gate_proj.weight": "model_layers_66_mlp_gate_proj_weight.safetensors",
    "model.layers.66.mlp.up_proj.weight": "model_layers_66_mlp_up_proj_weight.safetensors",
    "model.layers.66.post_attention_layernorm.weight": "model_layers_66_post_attention_layernorm_weight.safetensors",
    "model.layers.66.self_attn.k_proj.bias": "model_layers_66_self_attn_k_proj_bias.safetensors",
    "model.layers.66.self_attn.k_proj.weight": "model_layers_66_self_attn_k_proj_weight.safetensors",
    "model.layers.66.self_attn.o_proj.weight": "model_layers_66_self_attn_o_proj_weight.safetensors",
    "model.layers.66.self_attn.q_proj.bias": "model_layers_66_self_attn_q_proj_bias.safetensors",
    "model.layers.66.self_attn.q_proj.weight": "model_layers_66_self_attn_q_proj_weight.safetensors",
    "model.layers.66.self_attn.v_proj.bias": "model_layers_66_self_attn_v_proj_bias.safetensors",
    "model.layers.66.self_attn.v_proj.weight": "model_layers_66_self_attn_v_proj_weight.safetensors",
    "model.layers.67.input_layernorm.weight": "model_layers_67_input_layernorm_weight.safetensors",
    "model.layers.67.mlp.down_proj.weight": "model_layers_67_mlp_down_proj_weight.safetensors",
    "model.layers.67.mlp.gate_proj.weight": "model_layers_67_mlp_gate_proj_weight.safetensors",
    "model.layers.67.mlp.up_proj.weight": "model_layers_67_mlp_up_proj_weight.safetensors",
    "model.layers.67.post_attention_layernorm.weight": "model_layers_67_post_attention_layernorm_weight.safetensors",
    "model.layers.67.self_attn.k_proj.bias": "model_layers_67_self_attn_k_proj_bias.safetensors",
    "model.layers.67.self_attn.k_proj.weight": "model_layers_67_self_attn_k_proj_weight.safetensors",
    "model.layers.67.self_attn.o_proj.weight": "model_layers_67_self_attn_o_proj_weight.safetensors",
    "model.layers.67.self_attn.q_proj.bias": "model_layers_67_self_attn_q_proj_bias.safetensors",
    "model.layers.67.self_attn.q_proj.weight": "model_layers_67_self_attn_q_proj_weight.safetensors",
    "model.layers.67.self_attn.v_proj.bias": "model_layers_67_self_attn_v_proj_bias.safetensors",
    "model.layers.67.self_attn.v_proj.weight": "model_layers_67_self_attn_v_proj_weight.safetensors",
    "model.layers.68.input_layernorm.weight": "model_layers_68_input_layernorm_weight.safetensors",
    "model.layers.68.mlp.down_proj.weight": "model_layers_68_mlp_down_proj_weight.safetensors",
    "model.layers.68.mlp.gate_proj.weight": "model_layers_68_mlp_gate_proj_weight.safetensors",
    "model.layers.68.mlp.up_proj.weight": "model_layers_68_mlp_up_proj_weight.safetensors",
    "model.layers.68.post_attention_layernorm.weight": "model_layers_68_post_attention_layernorm_weight.safetensors",
    "model.layers.68.self_attn.k_proj.bias": "model_layers_68_self_attn_k_proj_bias.safetensors",
    "model.layers.68.self_attn.k_proj.weight": "model_layers_68_self_attn_k_proj_weight.safetensors",
    "model.layers.68.self_attn.o_proj.weight": "model_layers_68_self_attn_o_proj_weight.safetensors",
    "model.layers.68.self_attn.q_proj.bias": "model_layers_68_self_attn_q_proj_bias.safetensors",
    "model.layers.68.self_attn.q_proj.weight": "model_layers_68_self_attn_q_proj_weight.safetensors",
    "model.layers.68.self_attn.v_proj.bias": "model_layers_68_self_attn_v_proj_bias.safetensors",
    "model.layers.68.self_attn.v_proj.weight": "model_layers_68_self_attn_v_proj_weight.safetensors",
    "model.layers.69.input_layernorm.weight": "model_layers_69_input_layernorm_weight.safetensors",
    "model.layers.69.mlp.down_proj.weight": "model_layers_69_mlp_down_proj_weight.safetensors",
    "model.layers.69.mlp.gate_proj.weight": "model_layers_69_mlp_gate_proj_weight.safetensors",
    "model.layers.69.mlp.up_proj.weight": "model_layers_69_mlp_up_proj_weight.safetensors",
    "model.layers.69.post_attention_layernorm.weight": "model_layers_69_post_attention_layernorm_weight.safetensors",
    "model.layers.69.self_attn.k_proj.bias": "model_layers_69_self_attn_k_proj_bias.safetensors",
    "model.layers.69.self_attn.k_proj.weight": "model_layers_69_self_attn_k_proj_weight.safetensors",
    "model.layers.69.self_attn.o_proj.weight": "model_layers_69_self_attn_o_proj_weight.safetensors",
    "model.layers.69.self_attn.q_proj.bias": "model_layers_69_self_attn_q_proj_bias.safetensors",
    "model.layers.69.self_attn.q_proj.weight": "model_layers_69_self_attn_q_proj_weight.safetensors",
    "model.layers.69.self_attn.v_proj.bias": "model_layers_69_self_attn_v_proj_bias.safetensors",
    "model.layers.69.self_attn.v_proj.weight": "model_layers_69_self_attn_v_proj_weight.safetensors",
    "model.layers.6.input_layernorm.weight": "model_layers_6_input_layernorm_weight.safetensors",
    "model.layers.6.mlp.down_proj.weight": "model_layers_6_mlp_down_proj_weight.safetensors",
    "model.layers.6.mlp.gate_proj.weight": "model_layers_6_mlp_gate_proj_weight.safetensors",
    "model.layers.6.mlp.up_proj.weight": "model_layers_6_mlp_up_proj_weight.safetensors",
    "model.layers.6.post_attention_layernorm.weight": "model_layers_6_post_attention_layernorm_weight.safetensors",
    "model.layers.6.self_attn.k_proj.bias": "model_layers_6_self_attn_k_proj_bias.safetensors",
    "model.layers.6.self_attn.k_proj.weight": "model_layers_6_self_attn_k_proj_weight.safetensors",
    "model.layers.6.self_attn.o_proj.weight": "model_layers_6_self_attn_o_proj_weight.safetensors",
    "model.layers.6.self_attn.q_proj.bias": "model_layers_6_self_attn_q_proj_bias.safetensors",
    "model.layers.6.self_attn.q_proj.weight": "model_layers_6_self_attn_q_proj_weight.safetensors",
    "model.layers.6.self_attn.v_proj.bias": "model_layers_6_self_attn_v_proj_bias.safetensors",
    "model.layers.6.self_attn.v_proj.weight": "model_layers_6_self_attn_v_proj_weight.safetensors",
    "model.layers.70.input_layernorm.weight": "model_layers_70_input_layernorm_weight.safetensors",
    "model.layers.70.mlp.down_proj.weight": "model_layers_70_mlp_down_proj_weight.safetensors",
    "model.layers.70.mlp.gate_proj.weight": "model_layers_70_mlp_gate_proj_weight.safetensors",
    "model.layers.70.mlp.up_proj.weight": "model_layers_70_mlp_up_proj_weight.safetensors",
    "model.layers.70.post_attention_layernorm.weight": "model_layers_70_post_attention_layernorm_weight.safetensors",
    "model.layers.70.self_attn.k_proj.bias": "model_layers_70_self_attn_k_proj_bias.safetensors",
    "model.layers.70.self_attn.k_proj.weight": "model_layers_70_self_attn_k_proj_weight.safetensors",
    "model.layers.70.self_attn.o_proj.weight": "model_layers_70_self_attn_o_proj_weight.safetensors",
    "model.layers.70.self_attn.q_proj.bias": "model_layers_70_self_attn_q_proj_bias.safetensors",
    "model.layers.70.self_attn.q_proj.weight": "model_layers_70_self_attn_q_proj_weight.safetensors",
    "model.layers.70.self_attn.v_proj.bias": "model_layers_70_self_attn_v_proj_bias.safetensors",
    "model.layers.70.self_attn.v_proj.weight": "model_layers_70_self_attn_v_proj_weight.safetensors",
    "model.layers.71.input_layernorm.weight": "model_layers_71_input_layernorm_weight.safetensors",
    "model.layers.71.mlp.down_proj.weight": "model_layers_71_mlp_down_proj_weight.safetensors",
    "model.layers.71.mlp.gate_proj.weight": "model_layers_71_mlp_gate_proj_weight.safetensors",
    "model.layers.71.mlp.up_proj.weight": "model_layers_71_mlp_up_proj_weight.safetensors",
    "model.layers.71.post_attention_layernorm.weight": "model_layers_71_post_attention_layernorm_weight.safetensors",
    "model.layers.71.self_attn.k_proj.bias": "model_layers_71_self_attn_k_proj_bias.safetensors",
    "model.layers.71.self_attn.k_proj.weight": "model_layers_71_self_attn_k_proj_weight.safetensors",
    "model.layers.71.self_attn.o_proj.weight": "model_layers_71_self_attn_o_proj_weight.safetensors",
    "model.layers.71.self_attn.q_proj.bias": "model_layers_71_self_attn_q_proj_bias.safetensors",
    "model.layers.71.self_attn.q_proj.weight": "model_layers_71_self_attn_q_proj_weight.safetensors",
    "model.layers.71.self_attn.v_proj.bias": "model_layers_71_self_attn_v_proj_bias.safetensors",
    "model.layers.71.self_attn.v_proj.weight": "model_layers_71_self_attn_v_proj_weight.safetensors",
    "model.layers.72.input_layernorm.weight": "model_layers_72_input_layernorm_weight.safetensors",
    "model.layers.72.mlp.down_proj.weight": "model_layers_72_mlp_down_proj_weight.safetensors",
    "model.layers.72.mlp.gate_proj.weight": "model_layers_72_mlp_gate_proj_weight.safetensors",
    "model.layers.72.mlp.up_proj.weight": "model_layers_72_mlp_up_proj_weight.safetensors",
    "model.layers.72.post_attention_layernorm.weight": "model_layers_72_post_attention_layernorm_weight.safetensors",
    "model.layers.72.self_attn.k_proj.bias": "model_layers_72_self_attn_k_proj_bias.safetensors",
    "model.layers.72.self_attn.k_proj.weight": "model_layers_72_self_attn_k_proj_weight.safetensors",
    "model.layers.72.self_attn.o_proj.weight": "model_layers_72_self_attn_o_proj_weight.safetensors",
    "model.layers.72.self_attn.q_proj.bias": "model_layers_72_self_attn_q_proj_bias.safetensors",
    "model.layers.72.self_attn.q_proj.weight": "model_layers_72_self_attn_q_proj_weight.safetensors",
    "model.layers.72.self_attn.v_proj.bias": "model_layers_72_self_attn_v_proj_bias.safetensors",
    "model.layers.72.self_attn.v_proj.weight": "model_layers_72_self_attn_v_proj_weight.safetensors",
    "model.layers.73.input_layernorm.weight": "model_layers_73_input_layernorm_weight.safetensors",
    "model.layers.73.mlp.down_proj.weight": "model_layers_73_mlp_down_proj_weight.safetensors",
    "model.layers.73.mlp.gate_proj.weight": "model_layers_73_mlp_gate_proj_weight.safetensors",
    "model.layers.73.mlp.up_proj.weight": "model_layers_73_mlp_up_proj_weight.safetensors",
    "model.layers.73.post_attention_layernorm.weight": "model_layers_73_post_attention_layernorm_weight.safetensors",
    "model.layers.73.self_attn.k_proj.bias": "model_layers_73_self_attn_k_proj_bias.safetensors",
    "model.layers.73.self_attn.k_proj.weight": "model_layers_73_self_attn_k_proj_weight.safetensors",
    "model.layers.73.self_attn.o_proj.weight": "model_layers_73_self_attn_o_proj_weight.safetensors",
    "model.layers.73.self_attn.q_proj.bias": "model_layers_73_self_attn_q_proj_bias.safetensors",
    "model.layers.73.self_attn.q_proj.weight": "model_layers_73_self_attn_q_proj_weight.safetensors",
    "model.layers.73.self_attn.v_proj.bias": "model_layers_73_self_attn_v_proj_bias.safetensors",
    "model.layers.73.self_attn.v_proj.weight": "model_layers_73_self_attn_v_proj_weight.safetensors",
    "model.layers.74.input_layernorm.weight": "model_layers_74_input_layernorm_weight.safetensors",
    "model.layers.74.mlp.down_proj.weight": "model_layers_74_mlp_down_proj_weight.safetensors",
    "model.layers.74.mlp.gate_proj.weight": "model_layers_74_mlp_gate_proj_weight.safetensors",
    "model.layers.74.mlp.up_proj.weight": "model_layers_74_mlp_up_proj_weight.safetensors",
    "model.layers.74.post_attention_layernorm.weight": "model_layers_74_post_attention_layernorm_weight.safetensors",
    "model.layers.74.self_attn.k_proj.bias": "model_layers_74_self_attn_k_proj_bias.safetensors",
    "model.layers.74.self_attn.k_proj.weight": "model_layers_74_self_attn_k_proj_weight.safetensors",
    "model.layers.74.self_attn.o_proj.weight": "model_layers_74_self_attn_o_proj_weight.safetensors",
    "model.layers.74.self_attn.q_proj.bias": "model_layers_74_self_attn_q_proj_bias.safetensors",
    "model.layers.74.self_attn.q_proj.weight": "model_layers_74_self_attn_q_proj_weight.safetensors",
    "model.layers.74.self_attn.v_proj.bias": "model_layers_74_self_attn_v_proj_bias.safetensors",
    "model.layers.74.self_attn.v_proj.weight": "model_layers_74_self_attn_v_proj_weight.safetensors",
    "model.layers.75.input_layernorm.weight": "model_layers_75_input_layernorm_weight.safetensors",
    "model.layers.75.mlp.down_proj.weight": "model_layers_75_mlp_down_proj_weight.safetensors",
    "model.layers.75.mlp.gate_proj.weight": "model_layers_75_mlp_gate_proj_weight.safetensors",
    "model.layers.75.mlp.up_proj.weight": "model_layers_75_mlp_up_proj_weight.safetensors",
    "model.layers.75.post_attention_layernorm.weight": "model_layers_75_post_attention_layernorm_weight.safetensors",
    "model.layers.75.self_attn.k_proj.bias": "model_layers_75_self_attn_k_proj_bias.safetensors",
    "model.layers.75.self_attn.k_proj.weight": "model_layers_75_self_attn_k_proj_weight.safetensors",
    "model.layers.75.self_attn.o_proj.weight": "model_layers_75_self_attn_o_proj_weight.safetensors",
    "model.layers.75.self_attn.q_proj.bias": "model_layers_75_self_attn_q_proj_bias.safetensors",
    "model.layers.75.self_attn.q_proj.weight": "model_layers_75_self_attn_q_proj_weight.safetensors",
    "model.layers.75.self_attn.v_proj.bias": "model_layers_75_self_attn_v_proj_bias.safetensors",
    "model.layers.75.self_attn.v_proj.weight": "model_layers_75_self_attn_v_proj_weight.safetensors",
    "model.layers.76.input_layernorm.weight": "model_layers_76_input_layernorm_weight.safetensors",
    "model.layers.76.mlp.down_proj.weight": "model_layers_76_mlp_down_proj_weight.safetensors",
    "model.layers.76.mlp.gate_proj.weight": "model_layers_76_mlp_gate_proj_weight.safetensors",
    "model.layers.76.mlp.up_proj.weight": "model_layers_76_mlp_up_proj_weight.safetensors",
    "model.layers.76.post_attention_layernorm.weight": "model_layers_76_post_attention_layernorm_weight.safetensors",
    "model.layers.76.self_attn.k_proj.bias": "model_layers_76_self_attn_k_proj_bias.safetensors",
    "model.layers.76.self_attn.k_proj.weight": "model_layers_76_self_attn_k_proj_weight.safetensors",
    "model.layers.76.self_attn.o_proj.weight": "model_layers_76_self_attn_o_proj_weight.safetensors",
    "model.layers.76.self_attn.q_proj.bias": "model_layers_76_self_attn_q_proj_bias.safetensors",
    "model.layers.76.self_attn.q_proj.weight": "model_layers_76_self_attn_q_proj_weight.safetensors",
    "model.layers.76.self_attn.v_proj.bias": "model_layers_76_self_attn_v_proj_bias.safetensors",
    "model.layers.76.self_attn.v_proj.weight": "model_layers_76_self_attn_v_proj_weight.safetensors",
    "model.layers.77.input_layernorm.weight": "model_layers_77_input_layernorm_weight.safetensors",
    "model.layers.77.mlp.down_proj.weight": "model_layers_77_mlp_down_proj_weight.safetensors",
    "model.layers.77.mlp.gate_proj.weight": "model_layers_77_mlp_gate_proj_weight.safetensors",
    "model.layers.77.mlp.up_proj.weight": "model_layers_77_mlp_up_proj_weight.safetensors",
    "model.layers.77.post_attention_layernorm.weight": "model_layers_77_post_attention_layernorm_weight.safetensors",
    "model.layers.77.self_attn.k_proj.bias": "model_layers_77_self_attn_k_proj_bias.safetensors",
    "model.layers.77.self_attn.k_proj.weight": "model_layers_77_self_attn_k_proj_weight.safetensors",
    "model.layers.77.self_attn.o_proj.weight": "model_layers_77_self_attn_o_proj_weight.safetensors",
    "model.layers.77.self_attn.q_proj.bias": "model_layers_77_self_attn_q_proj_bias.safetensors",
    "model.layers.77.self_attn.q_proj.weight": "model_layers_77_self_attn_q_proj_weight.safetensors",
    "model.layers.77.self_attn.v_proj.bias": "model_layers_77_self_attn_v_proj_bias.safetensors",
    "model.layers.77.self_attn.v_proj.weight": "model_layers_77_self_attn_v_proj_weight.safetensors",
    "model.layers.78.input_layernorm.weight": "model_layers_78_input_layernorm_weight.safetensors",
    "model.layers.78.mlp.down_proj.weight": "model_layers_78_mlp_down_proj_weight.safetensors",
    "model.layers.78.mlp.gate_proj.weight": "model_layers_78_mlp_gate_proj_weight.safetensors",
    "model.layers.78.mlp.up_proj.weight": "model_layers_78_mlp_up_proj_weight.safetensors",
    "model.layers.78.post_attention_layernorm.weight": "model_layers_78_post_attention_layernorm_weight.safetensors",
    "model.layers.78.self_attn.k_proj.bias": "model_layers_78_self_attn_k_proj_bias.safetensors",
    "model.layers.78.self_attn.k_proj.weight": "model_layers_78_self_attn_k_proj_weight.safetensors",
    "model.layers.78.self_attn.o_proj.weight": "model_layers_78_self_attn_o_proj_weight.safetensors",
    "model.layers.78.self_attn.q_proj.bias": "model_layers_78_self_attn_q_proj_bias.safetensors",
    "model.layers.78.self_attn.q_proj.weight": "model_layers_78_self_attn_q_proj_weight.safetensors",
    "model.layers.78.self_attn.v_proj.bias": "model_layers_78_self_attn_v_proj_bias.safetensors",
    "model.layers.78.self_attn.v_proj.weight": "model_layers_78_self_attn_v_proj_weight.safetensors",
    "model.layers.79.input_layernorm.weight": "model_layers_79_input_layernorm_weight.safetensors",
    "model.layers.79.mlp.down_proj.weight": "model_layers_79_mlp_down_proj_weight.safetensors",
    "model.layers.79.mlp.gate_proj.weight": "model_layers_79_mlp_gate_proj_weight.safetensors",
    "model.layers.79.mlp.up_proj.weight": "model_layers_79_mlp_up_proj_weight.safetensors",
    "model.layers.79.post_attention_layernorm.weight": "model_layers_79_post_attention_layernorm_weight.safetensors",
    "model.layers.79.self_attn.k_proj.bias": "model_layers_79_self_attn_k_proj_bias.safetensors",
    "model.layers.79.self_attn.k_proj.weight": "model_layers_79_self_attn_k_proj_weight.safetensors",
    "model.layers.79.self_attn.o_proj.weight": "model_layers_79_self_attn_o_proj_weight.safetensors",
    "model.layers.79.self_attn.q_proj.bias": "model_layers_79_self_attn_q_proj_bias.safetensors",
    "model.layers.79.self_attn.q_proj.weight": "model_layers_79_self_attn_q_proj_weight.safetensors",
    "model.layers.79.self_attn.v_proj.bias": "model_layers_79_self_attn_v_proj_bias.safetensors",
    "model.layers.79.self_attn.v_proj.weight": "model_layers_79_self_attn_v_proj_weight.safetensors",
    "model.layers.7.input_layernorm.weight": "model_layers_7_input_layernorm_weight.safetensors",
    "model.layers.7.mlp.down_proj.weight": "model_layers_7_mlp_down_proj_weight.safetensors",
    "model.layers.7.mlp.gate_proj.weight": "model_layers_7_mlp_gate_proj_weight.safetensors",
    "model.layers.7.mlp.up_proj.weight": "model_layers_7_mlp_up_proj_weight.safetensors",
    "model.layers.7.post_attention_layernorm.weight": "model_layers_7_post_attention_layernorm_weight.safetensors",
    "model.layers.7.self_attn.k_proj.bias": "model_layers_7_self_attn_k_proj_bias.safetensors",
    "model.layers.7.self_attn.k_proj.weight": "model_layers_7_self_attn_k_proj_weight.safetensors",
    "model.layers.7.self_attn.o_proj.weight": "model_layers_7_self_attn_o_proj_weight.safetensors",
    "model.layers.7.self_attn.q_proj.bias": "model_layers_7_self_attn_q_proj_bias.safetensors",
    "model.layers.7.self_attn.q_proj.weight": "model_layers_7_self_attn_q_proj_weight.safetensors",
    "model.layers.7.self_attn.v_proj.bias": "model_layers_7_self_attn_v_proj_bias.safetensors",
    "model.layers.7.self_attn.v_proj.weight": "model_layers_7_self_attn_v_proj_weight.safetensors",
    "model.layers.8.input_layernorm.weight": "model_layers_8_input_layernorm_weight.safetensors",
    "model.layers.8.mlp.down_proj.weight": "model_layers_8_mlp_down_proj_weight.safetensors",
    "model.layers.8.mlp.gate_proj.weight": "model_layers_8_mlp_gate_proj_weight.safetensors",
    "model.layers.8.mlp.up_proj.weight": "model_layers_8_mlp_up_proj_weight.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model_layers_8_post_attention_layernorm_weight.safetensors",
    "model.layers.8.self_attn.k_proj.bias": "model_layers_8_self_attn_k_proj_bias.safetensors",
    "model.layers.8.self_attn.k_proj.weight": "model_layers_8_self_attn_k_proj_weight.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "model_layers_8_self_attn_o_proj_weight.safetensors",
    "model.layers.8.self_attn.q_proj.bias": "model_layers_8_self_attn_q_proj_bias.safetensors",
    "model.layers.8.self_attn.q_proj.weight": "model_layers_8_self_attn_q_proj_weight.safetensors",
    "model.layers.8.self_attn.v_proj.bias": "model_layers_8_self_attn_v_proj_bias.safetensors",
    "model.layers.8.self_attn.v_proj.weight": "model_layers_8_self_attn_v_proj_weight.safetensors",
    "model.layers.9.input_layernorm.weight": "model_layers_9_input_layernorm_weight.safetensors",
    "model.layers.9.mlp.down_proj.weight": "model_layers_9_mlp_down_proj_weight.safetensors",
    "model.layers.9.mlp.gate_proj.weight": "model_layers_9_mlp_gate_proj_weight.safetensors",
    "model.layers.9.mlp.up_proj.weight": "model_layers_9_mlp_up_proj_weight.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model_layers_9_post_attention_layernorm_weight.safetensors",
    "model.layers.9.self_attn.k_proj.bias": "model_layers_9_self_attn_k_proj_bias.safetensors",
    "model.layers.9.self_attn.k_proj.weight": "model_layers_9_self_attn_k_proj_weight.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "model_layers_9_self_attn_o_proj_weight.safetensors",
    "model.layers.9.self_attn.q_proj.bias": "model_layers_9_self_attn_q_proj_bias.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "model_layers_9_self_attn_q_proj_weight.safetensors",
    "model.layers.9.self_attn.v_proj.bias": "model_layers_9_self_attn_v_proj_bias.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "model_layers_9_self_attn_v_proj_weight.safetensors",
    "model.norm.weight": "model_norm_weight.safetensors"
  }
}