File size: 54,529 Bytes
cea5484
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "metadata": {
    "total_size": 13929963528
  },
  "weight_map": {
    "classifier.dense.bias": "model-00003-of-00003.safetensors",
    "classifier.dense.weight": "model-00003-of-00003.safetensors",
    "classifier.out_proj.bias": "model-00003-of-00003.safetensors",
    "classifier.out_proj.weight": "model-00003-of-00003.safetensors",
    "roberta.embeddings.position_embeddings.weight": "model-00001-of-00003.safetensors",
    "roberta.embeddings.token_type_embeddings.weight": "model-00001-of-00003.safetensors",
    "roberta.embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.0.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.10.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.10.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.11.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.12.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.13.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.14.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.15.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.16.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.17.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.18.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.19.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.2.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.20.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.20.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.21.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.22.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.23.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.23.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.23.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.23.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.23.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.24.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.25.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.26.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.27.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.28.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.29.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.3.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.3.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.30.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.30.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.31.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.32.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.33.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.34.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.LayerNorm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.LayerNorm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self.key.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self.key.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self.query.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self.query.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self.value.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self.value.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.intermediate.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.intermediate.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.output.dense.bias": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.35.output.dense.weight": "model-00003-of-00003.safetensors",
    "roberta.encoder.layer.4.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.4.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.5.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.LayerNorm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.LayerNorm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.6.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.7.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self.key.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self.key.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self.query.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self.query.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self.value.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self.value.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00003.safetensors",
    "roberta.encoder.layer.7.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.7.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.8.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.LayerNorm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.LayerNorm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self.key.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self.key.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self.query.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self.query.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self.value.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self.value.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.output.dense.bias": "model-00002-of-00003.safetensors",
    "roberta.encoder.layer.9.output.dense.weight": "model-00002-of-00003.safetensors"
  }
}