Hugging Face's logo

facebook
/
musicgen-stereo-large

Text-to-Audio
Transformers
PyTorch
Safetensors
Audiocraft
musicgen
Inference Endpoints
Model card Files Community
9
musicgen-stereo-large
File size: 103,753 Bytes 
af3486e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
 
{
  "metadata": {
    "total_size": 13853329688
  },
  "weight_map": {
    "audio_encoder.decoder.layers.0.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.0.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.0.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.10.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.10.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.10.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.10.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.12.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.12.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.12.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.13.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.13.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.13.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.13.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.13.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.13.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.15.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.15.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.15.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.4.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.4.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.4.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.4.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.4.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.4.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.6.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.6.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.6.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.7.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.7.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.7.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.7.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.7.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.7.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.9.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.9.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.decoder.layers.9.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.0.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.0.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.0.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.1.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.1.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.1.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.1.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.1.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.1.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.10.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.10.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.10.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.10.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.10.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.10.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.12.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.12.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.12.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.15.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.15.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.15.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.4.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.4.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.4.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.4.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.4.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.4.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.6.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.6.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.6.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.7.block.1.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.7.block.1.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.7.block.1.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.7.block.3.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.7.block.3.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.7.block.3.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.9.conv.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.9.conv.weight_g": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.encoder.layers.9.conv.weight_v": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.0.codebook.cluster_size": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.0.codebook.embed": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.0.codebook.embed_avg": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.0.codebook.inited": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.1.codebook.cluster_size": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.1.codebook.embed": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.1.codebook.embed_avg": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.1.codebook.inited": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.2.codebook.cluster_size": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.2.codebook.embed": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.2.codebook.embed_avg": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.2.codebook.inited": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.3.codebook.cluster_size": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.3.codebook.embed": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.3.codebook.embed_avg": "pytorch_model.fp32-00001-of-00003.bin",
    "audio_encoder.quantizer.layers.3.codebook.inited": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.lm_heads.0.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.3.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.4.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.5.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.6.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.lm_heads.7.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.embed_positions.weights": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.0.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.3.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.4.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.5.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.6.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.embed_tokens.7.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.15.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.15.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.15.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.16.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.encoder_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.encoder_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.encoder_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.encoder_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.fc1.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.fc2.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.final_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.final_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.self_attn.out_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.34.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model.fp32-00002-of-00003.bin",
    "decoder.model.decoder.layers.34.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.40.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.40.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.41.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.42.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.43.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.45.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.46.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.encoder_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.encoder_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.encoder_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.encoder_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.fc1.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.fc2.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.final_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.final_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.self_attn.k_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.self_attn.out_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.self_attn.q_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.self_attn.v_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.self_attn_layer_norm.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.47.self_attn_layer_norm.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.fc1.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.fc2.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.final_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model.fp32-00001-of-00003.bin",
    "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "enc_to_dec_proj.bias": "pytorch_model.fp32-00003-of-00003.bin",
    "enc_to_dec_proj.weight": "pytorch_model.fp32-00003-of-00003.bin",
    "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.embed_tokens.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.encoder.final_layer_norm.weight": "pytorch_model.fp32-00001-of-00003.bin",
    "text_encoder.shared.weight": "pytorch_model.fp32-00001-of-00003.bin"
  }
}