Danda245 commited on
Commit
f4d5435
·
verified ·
1 Parent(s): 31c0ab9

Upload 8 files

Browse files
Files changed (7) hide show
  1. config.json +69 -69
  2. generation_config.json +8 -8
  3. merges.txt +0 -0
  4. special_tokens_map.json +753 -753
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +959 -959
  7. vocab.json +0 -0
config.json CHANGED
@@ -1,69 +1,69 @@
1
- {
2
- "_name_or_path": "Danda245/CodeT5-base_code-refinement",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
5
- ],
6
- "bos_token_id": 1,
7
- "classifier_dropout": 0.0,
8
- "d_ff": 3072,
9
- "d_kv": 64,
10
- "d_model": 768,
11
- "decoder_start_token_id": 0,
12
- "dense_act_fn": "relu",
13
- "dropout_rate": 0.1,
14
- "eos_token_id": 2,
15
- "feed_forward_proj": "relu",
16
- "gradient_checkpointing": false,
17
- "id2label": {
18
- "0": "LABEL_0"
19
- },
20
- "initializer_factor": 1.0,
21
- "is_encoder_decoder": true,
22
- "is_gated_act": false,
23
- "label2id": {
24
- "LABEL_0": 0
25
- },
26
- "layer_norm_epsilon": 1e-06,
27
- "model_type": "t5",
28
- "n_positions": 512,
29
- "num_decoder_layers": 12,
30
- "num_heads": 12,
31
- "num_layers": 12,
32
- "output_past": true,
33
- "pad_token_id": 0,
34
- "relative_attention_max_distance": 128,
35
- "relative_attention_num_buckets": 32,
36
- "task_specific_params": {
37
- "summarization": {
38
- "early_stopping": true,
39
- "length_penalty": 2.0,
40
- "max_length": 200,
41
- "min_length": 30,
42
- "no_repeat_ngram_size": 3,
43
- "num_beams": 4,
44
- "prefix": "summarize: "
45
- },
46
- "translation_en_to_de": {
47
- "early_stopping": true,
48
- "max_length": 300,
49
- "num_beams": 4,
50
- "prefix": "translate English to German: "
51
- },
52
- "translation_en_to_fr": {
53
- "early_stopping": true,
54
- "max_length": 300,
55
- "num_beams": 4,
56
- "prefix": "translate English to French: "
57
- },
58
- "translation_en_to_ro": {
59
- "early_stopping": true,
60
- "max_length": 300,
61
- "num_beams": 4,
62
- "prefix": "translate English to Romanian: "
63
- }
64
- },
65
- "torch_dtype": "float32",
66
- "transformers_version": "4.46.3",
67
- "use_cache": true,
68
- "vocab_size": 32100
69
- }
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "model_type": "t5",
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 12,
30
+ "num_heads": 12,
31
+ "num_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "relative_attention_max_distance": 128,
35
+ "relative_attention_num_buckets": 32,
36
+ "task_specific_params": {
37
+ "summarization": {
38
+ "early_stopping": true,
39
+ "length_penalty": 2.0,
40
+ "max_length": 200,
41
+ "min_length": 30,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 4,
44
+ "prefix": "summarize: "
45
+ },
46
+ "translation_en_to_de": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to German: "
51
+ },
52
+ "translation_en_to_fr": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to French: "
57
+ },
58
+ "translation_en_to_ro": {
59
+ "early_stopping": true,
60
+ "max_length": 300,
61
+ "num_beams": 4,
62
+ "prefix": "translate English to Romanian: "
63
+ }
64
+ },
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.46.3",
67
+ "use_cache": true,
68
+ "vocab_size": 32100
69
+ }
generation_config.json CHANGED
@@ -1,8 +1,8 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "decoder_start_token_id": 0,
5
- "eos_token_id": 2,
6
- "pad_token_id": 0,
7
- "transformers_version": "4.46.3"
8
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.46.3"
8
+ }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,753 +1,753 @@
1
- {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<extra_id_99>",
5
- "lstrip": true,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<extra_id_98>",
12
- "lstrip": true,
13
- "normalized": true,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "<extra_id_97>",
19
- "lstrip": true,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "<extra_id_96>",
26
- "lstrip": true,
27
- "normalized": true,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "<extra_id_95>",
33
- "lstrip": true,
34
- "normalized": true,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
- {
39
- "content": "<extra_id_94>",
40
- "lstrip": true,
41
- "normalized": true,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- {
46
- "content": "<extra_id_93>",
47
- "lstrip": true,
48
- "normalized": true,
49
- "rstrip": false,
50
- "single_word": false
51
- },
52
- {
53
- "content": "<extra_id_92>",
54
- "lstrip": true,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false
58
- },
59
- {
60
- "content": "<extra_id_91>",
61
- "lstrip": true,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false
65
- },
66
- {
67
- "content": "<extra_id_90>",
68
- "lstrip": true,
69
- "normalized": true,
70
- "rstrip": false,
71
- "single_word": false
72
- },
73
- {
74
- "content": "<extra_id_89>",
75
- "lstrip": true,
76
- "normalized": true,
77
- "rstrip": false,
78
- "single_word": false
79
- },
80
- {
81
- "content": "<extra_id_88>",
82
- "lstrip": true,
83
- "normalized": true,
84
- "rstrip": false,
85
- "single_word": false
86
- },
87
- {
88
- "content": "<extra_id_87>",
89
- "lstrip": true,
90
- "normalized": true,
91
- "rstrip": false,
92
- "single_word": false
93
- },
94
- {
95
- "content": "<extra_id_86>",
96
- "lstrip": true,
97
- "normalized": true,
98
- "rstrip": false,
99
- "single_word": false
100
- },
101
- {
102
- "content": "<extra_id_85>",
103
- "lstrip": true,
104
- "normalized": true,
105
- "rstrip": false,
106
- "single_word": false
107
- },
108
- {
109
- "content": "<extra_id_84>",
110
- "lstrip": true,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false
114
- },
115
- {
116
- "content": "<extra_id_83>",
117
- "lstrip": true,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": false
121
- },
122
- {
123
- "content": "<extra_id_82>",
124
- "lstrip": true,
125
- "normalized": true,
126
- "rstrip": false,
127
- "single_word": false
128
- },
129
- {
130
- "content": "<extra_id_81>",
131
- "lstrip": true,
132
- "normalized": true,
133
- "rstrip": false,
134
- "single_word": false
135
- },
136
- {
137
- "content": "<extra_id_80>",
138
- "lstrip": true,
139
- "normalized": true,
140
- "rstrip": false,
141
- "single_word": false
142
- },
143
- {
144
- "content": "<extra_id_79>",
145
- "lstrip": true,
146
- "normalized": true,
147
- "rstrip": false,
148
- "single_word": false
149
- },
150
- {
151
- "content": "<extra_id_78>",
152
- "lstrip": true,
153
- "normalized": true,
154
- "rstrip": false,
155
- "single_word": false
156
- },
157
- {
158
- "content": "<extra_id_77>",
159
- "lstrip": true,
160
- "normalized": true,
161
- "rstrip": false,
162
- "single_word": false
163
- },
164
- {
165
- "content": "<extra_id_76>",
166
- "lstrip": true,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false
170
- },
171
- {
172
- "content": "<extra_id_75>",
173
- "lstrip": true,
174
- "normalized": true,
175
- "rstrip": false,
176
- "single_word": false
177
- },
178
- {
179
- "content": "<extra_id_74>",
180
- "lstrip": true,
181
- "normalized": true,
182
- "rstrip": false,
183
- "single_word": false
184
- },
185
- {
186
- "content": "<extra_id_73>",
187
- "lstrip": true,
188
- "normalized": true,
189
- "rstrip": false,
190
- "single_word": false
191
- },
192
- {
193
- "content": "<extra_id_72>",
194
- "lstrip": true,
195
- "normalized": true,
196
- "rstrip": false,
197
- "single_word": false
198
- },
199
- {
200
- "content": "<extra_id_71>",
201
- "lstrip": true,
202
- "normalized": true,
203
- "rstrip": false,
204
- "single_word": false
205
- },
206
- {
207
- "content": "<extra_id_70>",
208
- "lstrip": true,
209
- "normalized": true,
210
- "rstrip": false,
211
- "single_word": false
212
- },
213
- {
214
- "content": "<extra_id_69>",
215
- "lstrip": true,
216
- "normalized": true,
217
- "rstrip": false,
218
- "single_word": false
219
- },
220
- {
221
- "content": "<extra_id_68>",
222
- "lstrip": true,
223
- "normalized": true,
224
- "rstrip": false,
225
- "single_word": false
226
- },
227
- {
228
- "content": "<extra_id_67>",
229
- "lstrip": true,
230
- "normalized": true,
231
- "rstrip": false,
232
- "single_word": false
233
- },
234
- {
235
- "content": "<extra_id_66>",
236
- "lstrip": true,
237
- "normalized": true,
238
- "rstrip": false,
239
- "single_word": false
240
- },
241
- {
242
- "content": "<extra_id_65>",
243
- "lstrip": true,
244
- "normalized": true,
245
- "rstrip": false,
246
- "single_word": false
247
- },
248
- {
249
- "content": "<extra_id_64>",
250
- "lstrip": true,
251
- "normalized": true,
252
- "rstrip": false,
253
- "single_word": false
254
- },
255
- {
256
- "content": "<extra_id_63>",
257
- "lstrip": true,
258
- "normalized": true,
259
- "rstrip": false,
260
- "single_word": false
261
- },
262
- {
263
- "content": "<extra_id_62>",
264
- "lstrip": true,
265
- "normalized": true,
266
- "rstrip": false,
267
- "single_word": false
268
- },
269
- {
270
- "content": "<extra_id_61>",
271
- "lstrip": true,
272
- "normalized": true,
273
- "rstrip": false,
274
- "single_word": false
275
- },
276
- {
277
- "content": "<extra_id_60>",
278
- "lstrip": true,
279
- "normalized": true,
280
- "rstrip": false,
281
- "single_word": false
282
- },
283
- {
284
- "content": "<extra_id_59>",
285
- "lstrip": true,
286
- "normalized": true,
287
- "rstrip": false,
288
- "single_word": false
289
- },
290
- {
291
- "content": "<extra_id_58>",
292
- "lstrip": true,
293
- "normalized": true,
294
- "rstrip": false,
295
- "single_word": false
296
- },
297
- {
298
- "content": "<extra_id_57>",
299
- "lstrip": true,
300
- "normalized": true,
301
- "rstrip": false,
302
- "single_word": false
303
- },
304
- {
305
- "content": "<extra_id_56>",
306
- "lstrip": true,
307
- "normalized": true,
308
- "rstrip": false,
309
- "single_word": false
310
- },
311
- {
312
- "content": "<extra_id_55>",
313
- "lstrip": true,
314
- "normalized": true,
315
- "rstrip": false,
316
- "single_word": false
317
- },
318
- {
319
- "content": "<extra_id_54>",
320
- "lstrip": true,
321
- "normalized": true,
322
- "rstrip": false,
323
- "single_word": false
324
- },
325
- {
326
- "content": "<extra_id_53>",
327
- "lstrip": true,
328
- "normalized": true,
329
- "rstrip": false,
330
- "single_word": false
331
- },
332
- {
333
- "content": "<extra_id_52>",
334
- "lstrip": true,
335
- "normalized": true,
336
- "rstrip": false,
337
- "single_word": false
338
- },
339
- {
340
- "content": "<extra_id_51>",
341
- "lstrip": true,
342
- "normalized": true,
343
- "rstrip": false,
344
- "single_word": false
345
- },
346
- {
347
- "content": "<extra_id_50>",
348
- "lstrip": true,
349
- "normalized": true,
350
- "rstrip": false,
351
- "single_word": false
352
- },
353
- {
354
- "content": "<extra_id_49>",
355
- "lstrip": true,
356
- "normalized": true,
357
- "rstrip": false,
358
- "single_word": false
359
- },
360
- {
361
- "content": "<extra_id_48>",
362
- "lstrip": true,
363
- "normalized": true,
364
- "rstrip": false,
365
- "single_word": false
366
- },
367
- {
368
- "content": "<extra_id_47>",
369
- "lstrip": true,
370
- "normalized": true,
371
- "rstrip": false,
372
- "single_word": false
373
- },
374
- {
375
- "content": "<extra_id_46>",
376
- "lstrip": true,
377
- "normalized": true,
378
- "rstrip": false,
379
- "single_word": false
380
- },
381
- {
382
- "content": "<extra_id_45>",
383
- "lstrip": true,
384
- "normalized": true,
385
- "rstrip": false,
386
- "single_word": false
387
- },
388
- {
389
- "content": "<extra_id_44>",
390
- "lstrip": true,
391
- "normalized": true,
392
- "rstrip": false,
393
- "single_word": false
394
- },
395
- {
396
- "content": "<extra_id_43>",
397
- "lstrip": true,
398
- "normalized": true,
399
- "rstrip": false,
400
- "single_word": false
401
- },
402
- {
403
- "content": "<extra_id_42>",
404
- "lstrip": true,
405
- "normalized": true,
406
- "rstrip": false,
407
- "single_word": false
408
- },
409
- {
410
- "content": "<extra_id_41>",
411
- "lstrip": true,
412
- "normalized": true,
413
- "rstrip": false,
414
- "single_word": false
415
- },
416
- {
417
- "content": "<extra_id_40>",
418
- "lstrip": true,
419
- "normalized": true,
420
- "rstrip": false,
421
- "single_word": false
422
- },
423
- {
424
- "content": "<extra_id_39>",
425
- "lstrip": true,
426
- "normalized": true,
427
- "rstrip": false,
428
- "single_word": false
429
- },
430
- {
431
- "content": "<extra_id_38>",
432
- "lstrip": true,
433
- "normalized": true,
434
- "rstrip": false,
435
- "single_word": false
436
- },
437
- {
438
- "content": "<extra_id_37>",
439
- "lstrip": true,
440
- "normalized": true,
441
- "rstrip": false,
442
- "single_word": false
443
- },
444
- {
445
- "content": "<extra_id_36>",
446
- "lstrip": true,
447
- "normalized": true,
448
- "rstrip": false,
449
- "single_word": false
450
- },
451
- {
452
- "content": "<extra_id_35>",
453
- "lstrip": true,
454
- "normalized": true,
455
- "rstrip": false,
456
- "single_word": false
457
- },
458
- {
459
- "content": "<extra_id_34>",
460
- "lstrip": true,
461
- "normalized": true,
462
- "rstrip": false,
463
- "single_word": false
464
- },
465
- {
466
- "content": "<extra_id_33>",
467
- "lstrip": true,
468
- "normalized": true,
469
- "rstrip": false,
470
- "single_word": false
471
- },
472
- {
473
- "content": "<extra_id_32>",
474
- "lstrip": true,
475
- "normalized": true,
476
- "rstrip": false,
477
- "single_word": false
478
- },
479
- {
480
- "content": "<extra_id_31>",
481
- "lstrip": true,
482
- "normalized": true,
483
- "rstrip": false,
484
- "single_word": false
485
- },
486
- {
487
- "content": "<extra_id_30>",
488
- "lstrip": true,
489
- "normalized": true,
490
- "rstrip": false,
491
- "single_word": false
492
- },
493
- {
494
- "content": "<extra_id_29>",
495
- "lstrip": true,
496
- "normalized": true,
497
- "rstrip": false,
498
- "single_word": false
499
- },
500
- {
501
- "content": "<extra_id_28>",
502
- "lstrip": true,
503
- "normalized": true,
504
- "rstrip": false,
505
- "single_word": false
506
- },
507
- {
508
- "content": "<extra_id_27>",
509
- "lstrip": true,
510
- "normalized": true,
511
- "rstrip": false,
512
- "single_word": false
513
- },
514
- {
515
- "content": "<extra_id_26>",
516
- "lstrip": true,
517
- "normalized": true,
518
- "rstrip": false,
519
- "single_word": false
520
- },
521
- {
522
- "content": "<extra_id_25>",
523
- "lstrip": true,
524
- "normalized": true,
525
- "rstrip": false,
526
- "single_word": false
527
- },
528
- {
529
- "content": "<extra_id_24>",
530
- "lstrip": true,
531
- "normalized": true,
532
- "rstrip": false,
533
- "single_word": false
534
- },
535
- {
536
- "content": "<extra_id_23>",
537
- "lstrip": true,
538
- "normalized": true,
539
- "rstrip": false,
540
- "single_word": false
541
- },
542
- {
543
- "content": "<extra_id_22>",
544
- "lstrip": true,
545
- "normalized": true,
546
- "rstrip": false,
547
- "single_word": false
548
- },
549
- {
550
- "content": "<extra_id_21>",
551
- "lstrip": true,
552
- "normalized": true,
553
- "rstrip": false,
554
- "single_word": false
555
- },
556
- {
557
- "content": "<extra_id_20>",
558
- "lstrip": true,
559
- "normalized": true,
560
- "rstrip": false,
561
- "single_word": false
562
- },
563
- {
564
- "content": "<extra_id_19>",
565
- "lstrip": true,
566
- "normalized": true,
567
- "rstrip": false,
568
- "single_word": false
569
- },
570
- {
571
- "content": "<extra_id_18>",
572
- "lstrip": true,
573
- "normalized": true,
574
- "rstrip": false,
575
- "single_word": false
576
- },
577
- {
578
- "content": "<extra_id_17>",
579
- "lstrip": true,
580
- "normalized": true,
581
- "rstrip": false,
582
- "single_word": false
583
- },
584
- {
585
- "content": "<extra_id_16>",
586
- "lstrip": true,
587
- "normalized": true,
588
- "rstrip": false,
589
- "single_word": false
590
- },
591
- {
592
- "content": "<extra_id_15>",
593
- "lstrip": true,
594
- "normalized": true,
595
- "rstrip": false,
596
- "single_word": false
597
- },
598
- {
599
- "content": "<extra_id_14>",
600
- "lstrip": true,
601
- "normalized": true,
602
- "rstrip": false,
603
- "single_word": false
604
- },
605
- {
606
- "content": "<extra_id_13>",
607
- "lstrip": true,
608
- "normalized": true,
609
- "rstrip": false,
610
- "single_word": false
611
- },
612
- {
613
- "content": "<extra_id_12>",
614
- "lstrip": true,
615
- "normalized": true,
616
- "rstrip": false,
617
- "single_word": false
618
- },
619
- {
620
- "content": "<extra_id_11>",
621
- "lstrip": true,
622
- "normalized": true,
623
- "rstrip": false,
624
- "single_word": false
625
- },
626
- {
627
- "content": "<extra_id_10>",
628
- "lstrip": true,
629
- "normalized": true,
630
- "rstrip": false,
631
- "single_word": false
632
- },
633
- {
634
- "content": "<extra_id_9>",
635
- "lstrip": true,
636
- "normalized": true,
637
- "rstrip": false,
638
- "single_word": false
639
- },
640
- {
641
- "content": "<extra_id_8>",
642
- "lstrip": true,
643
- "normalized": true,
644
- "rstrip": false,
645
- "single_word": false
646
- },
647
- {
648
- "content": "<extra_id_7>",
649
- "lstrip": true,
650
- "normalized": true,
651
- "rstrip": false,
652
- "single_word": false
653
- },
654
- {
655
- "content": "<extra_id_6>",
656
- "lstrip": true,
657
- "normalized": true,
658
- "rstrip": false,
659
- "single_word": false
660
- },
661
- {
662
- "content": "<extra_id_5>",
663
- "lstrip": true,
664
- "normalized": true,
665
- "rstrip": false,
666
- "single_word": false
667
- },
668
- {
669
- "content": "<extra_id_4>",
670
- "lstrip": true,
671
- "normalized": true,
672
- "rstrip": false,
673
- "single_word": false
674
- },
675
- {
676
- "content": "<extra_id_3>",
677
- "lstrip": true,
678
- "normalized": true,
679
- "rstrip": false,
680
- "single_word": false
681
- },
682
- {
683
- "content": "<extra_id_2>",
684
- "lstrip": true,
685
- "normalized": true,
686
- "rstrip": false,
687
- "single_word": false
688
- },
689
- {
690
- "content": "<extra_id_1>",
691
- "lstrip": true,
692
- "normalized": true,
693
- "rstrip": false,
694
- "single_word": false
695
- },
696
- {
697
- "content": "<extra_id_0>",
698
- "lstrip": true,
699
- "normalized": true,
700
- "rstrip": false,
701
- "single_word": false
702
- }
703
- ],
704
- "bos_token": {
705
- "content": "<s>",
706
- "lstrip": false,
707
- "normalized": true,
708
- "rstrip": false,
709
- "single_word": false
710
- },
711
- "cls_token": {
712
- "content": "<s>",
713
- "lstrip": false,
714
- "normalized": true,
715
- "rstrip": false,
716
- "single_word": false
717
- },
718
- "eos_token": {
719
- "content": "</s>",
720
- "lstrip": false,
721
- "normalized": true,
722
- "rstrip": false,
723
- "single_word": false
724
- },
725
- "mask_token": {
726
- "content": "<mask>",
727
- "lstrip": true,
728
- "normalized": true,
729
- "rstrip": false,
730
- "single_word": false
731
- },
732
- "pad_token": {
733
- "content": "<pad>",
734
- "lstrip": false,
735
- "normalized": true,
736
- "rstrip": false,
737
- "single_word": false
738
- },
739
- "sep_token": {
740
- "content": "</s>",
741
- "lstrip": false,
742
- "normalized": true,
743
- "rstrip": false,
744
- "single_word": false
745
- },
746
- "unk_token": {
747
- "content": "<unk>",
748
- "lstrip": false,
749
- "normalized": true,
750
- "rstrip": false,
751
- "single_word": false
752
- }
753
- }
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<extra_id_99>",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<extra_id_98>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<extra_id_97>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<extra_id_96>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<extra_id_95>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<extra_id_94>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<extra_id_93>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<extra_id_92>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<extra_id_90>",
68
+ "lstrip": true,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<extra_id_89>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<extra_id_88>",
82
+ "lstrip": true,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<extra_id_87>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<extra_id_86>",
96
+ "lstrip": true,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<extra_id_85>",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<extra_id_84>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<extra_id_83>",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<extra_id_82>",
124
+ "lstrip": true,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<extra_id_81>",
131
+ "lstrip": true,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<extra_id_80>",
138
+ "lstrip": true,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<extra_id_79>",
145
+ "lstrip": true,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<extra_id_78>",
152
+ "lstrip": true,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<extra_id_77>",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<extra_id_76>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<extra_id_75>",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<extra_id_74>",
180
+ "lstrip": true,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<extra_id_73>",
187
+ "lstrip": true,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<extra_id_72>",
194
+ "lstrip": true,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<extra_id_71>",
201
+ "lstrip": true,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<extra_id_70>",
208
+ "lstrip": true,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<extra_id_69>",
215
+ "lstrip": true,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<extra_id_68>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<extra_id_67>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<extra_id_66>",
236
+ "lstrip": true,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<extra_id_65>",
243
+ "lstrip": true,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<extra_id_64>",
250
+ "lstrip": true,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<extra_id_63>",
257
+ "lstrip": true,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<extra_id_62>",
264
+ "lstrip": true,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<extra_id_61>",
271
+ "lstrip": true,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<extra_id_60>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<extra_id_59>",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<extra_id_58>",
292
+ "lstrip": true,
293
+ "normalized": true,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<extra_id_57>",
299
+ "lstrip": true,
300
+ "normalized": true,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<extra_id_56>",
306
+ "lstrip": true,
307
+ "normalized": true,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<extra_id_55>",
313
+ "lstrip": true,
314
+ "normalized": true,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<extra_id_54>",
320
+ "lstrip": true,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<extra_id_53>",
327
+ "lstrip": true,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<extra_id_52>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<extra_id_51>",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<extra_id_50>",
348
+ "lstrip": true,
349
+ "normalized": true,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<extra_id_49>",
355
+ "lstrip": true,
356
+ "normalized": true,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<extra_id_48>",
362
+ "lstrip": true,
363
+ "normalized": true,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<extra_id_47>",
369
+ "lstrip": true,
370
+ "normalized": true,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<extra_id_46>",
376
+ "lstrip": true,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<extra_id_45>",
383
+ "lstrip": true,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<extra_id_43>",
397
+ "lstrip": true,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<extra_id_42>",
404
+ "lstrip": true,
405
+ "normalized": true,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<extra_id_41>",
411
+ "lstrip": true,
412
+ "normalized": true,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<extra_id_40>",
418
+ "lstrip": true,
419
+ "normalized": true,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<extra_id_39>",
425
+ "lstrip": true,
426
+ "normalized": true,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<extra_id_38>",
432
+ "lstrip": true,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<extra_id_37>",
439
+ "lstrip": true,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<extra_id_36>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<extra_id_35>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<extra_id_34>",
460
+ "lstrip": true,
461
+ "normalized": true,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<extra_id_33>",
467
+ "lstrip": true,
468
+ "normalized": true,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<extra_id_32>",
474
+ "lstrip": true,
475
+ "normalized": true,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<extra_id_31>",
481
+ "lstrip": true,
482
+ "normalized": true,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<extra_id_30>",
488
+ "lstrip": true,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<extra_id_29>",
495
+ "lstrip": true,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<extra_id_28>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<extra_id_27>",
509
+ "lstrip": true,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<extra_id_26>",
516
+ "lstrip": true,
517
+ "normalized": true,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<extra_id_25>",
523
+ "lstrip": true,
524
+ "normalized": true,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<extra_id_24>",
530
+ "lstrip": true,
531
+ "normalized": true,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<extra_id_23>",
537
+ "lstrip": true,
538
+ "normalized": true,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<extra_id_22>",
544
+ "lstrip": true,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<extra_id_21>",
551
+ "lstrip": true,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<extra_id_20>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<extra_id_19>",
565
+ "lstrip": true,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<extra_id_18>",
572
+ "lstrip": true,
573
+ "normalized": true,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<extra_id_17>",
579
+ "lstrip": true,
580
+ "normalized": true,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<extra_id_16>",
586
+ "lstrip": true,
587
+ "normalized": true,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<extra_id_15>",
593
+ "lstrip": true,
594
+ "normalized": true,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<extra_id_14>",
600
+ "lstrip": true,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<extra_id_13>",
607
+ "lstrip": true,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<extra_id_12>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<extra_id_11>",
621
+ "lstrip": true,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<extra_id_10>",
628
+ "lstrip": true,
629
+ "normalized": true,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<extra_id_9>",
635
+ "lstrip": true,
636
+ "normalized": true,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "<extra_id_8>",
642
+ "lstrip": true,
643
+ "normalized": true,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<extra_id_7>",
649
+ "lstrip": true,
650
+ "normalized": true,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "<extra_id_6>",
656
+ "lstrip": true,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<extra_id_5>",
663
+ "lstrip": true,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "<extra_id_4>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<extra_id_3>",
677
+ "lstrip": true,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<extra_id_2>",
684
+ "lstrip": true,
685
+ "normalized": true,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<extra_id_1>",
691
+ "lstrip": true,
692
+ "normalized": true,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<extra_id_0>",
698
+ "lstrip": true,
699
+ "normalized": true,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ }
703
+ ],
704
+ "bos_token": {
705
+ "content": "<s>",
706
+ "lstrip": false,
707
+ "normalized": true,
708
+ "rstrip": false,
709
+ "single_word": false
710
+ },
711
+ "cls_token": {
712
+ "content": "<s>",
713
+ "lstrip": false,
714
+ "normalized": true,
715
+ "rstrip": false,
716
+ "single_word": false
717
+ },
718
+ "eos_token": {
719
+ "content": "</s>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false
724
+ },
725
+ "mask_token": {
726
+ "content": "<mask>",
727
+ "lstrip": true,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "<pad>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "sep_token": {
740
+ "content": "</s>",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ },
746
+ "unk_token": {
747
+ "content": "<unk>",
748
+ "lstrip": false,
749
+ "normalized": true,
750
+ "rstrip": false,
751
+ "single_word": false
752
+ }
753
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,959 +1,959 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "32000": {
45
- "content": "<extra_id_99>",
46
- "lstrip": true,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "32001": {
53
- "content": "<extra_id_98>",
54
- "lstrip": true,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "32002": {
61
- "content": "<extra_id_97>",
62
- "lstrip": true,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "32003": {
69
- "content": "<extra_id_96>",
70
- "lstrip": true,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "32004": {
77
- "content": "<extra_id_95>",
78
- "lstrip": true,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "32005": {
85
- "content": "<extra_id_94>",
86
- "lstrip": true,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "32006": {
93
- "content": "<extra_id_93>",
94
- "lstrip": true,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "32007": {
101
- "content": "<extra_id_92>",
102
- "lstrip": true,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "32008": {
109
- "content": "<extra_id_91>",
110
- "lstrip": true,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "32009": {
117
- "content": "<extra_id_90>",
118
- "lstrip": true,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "32010": {
125
- "content": "<extra_id_89>",
126
- "lstrip": true,
127
- "normalized": true,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "32011": {
133
- "content": "<extra_id_88>",
134
- "lstrip": true,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "32012": {
141
- "content": "<extra_id_87>",
142
- "lstrip": true,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "32013": {
149
- "content": "<extra_id_86>",
150
- "lstrip": true,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "32014": {
157
- "content": "<extra_id_85>",
158
- "lstrip": true,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "32015": {
165
- "content": "<extra_id_84>",
166
- "lstrip": true,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "32016": {
173
- "content": "<extra_id_83>",
174
- "lstrip": true,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "32017": {
181
- "content": "<extra_id_82>",
182
- "lstrip": true,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "32018": {
189
- "content": "<extra_id_81>",
190
- "lstrip": true,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": true
195
- },
196
- "32019": {
197
- "content": "<extra_id_80>",
198
- "lstrip": true,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": true
203
- },
204
- "32020": {
205
- "content": "<extra_id_79>",
206
- "lstrip": true,
207
- "normalized": true,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "32021": {
213
- "content": "<extra_id_78>",
214
- "lstrip": true,
215
- "normalized": true,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "32022": {
221
- "content": "<extra_id_77>",
222
- "lstrip": true,
223
- "normalized": true,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "32023": {
229
- "content": "<extra_id_76>",
230
- "lstrip": true,
231
- "normalized": true,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "32024": {
237
- "content": "<extra_id_75>",
238
- "lstrip": true,
239
- "normalized": true,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "32025": {
245
- "content": "<extra_id_74>",
246
- "lstrip": true,
247
- "normalized": true,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "32026": {
253
- "content": "<extra_id_73>",
254
- "lstrip": true,
255
- "normalized": true,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "32027": {
261
- "content": "<extra_id_72>",
262
- "lstrip": true,
263
- "normalized": true,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- },
268
- "32028": {
269
- "content": "<extra_id_71>",
270
- "lstrip": true,
271
- "normalized": true,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": true
275
- },
276
- "32029": {
277
- "content": "<extra_id_70>",
278
- "lstrip": true,
279
- "normalized": true,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": true
283
- },
284
- "32030": {
285
- "content": "<extra_id_69>",
286
- "lstrip": true,
287
- "normalized": true,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": true
291
- },
292
- "32031": {
293
- "content": "<extra_id_68>",
294
- "lstrip": true,
295
- "normalized": true,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": true
299
- },
300
- "32032": {
301
- "content": "<extra_id_67>",
302
- "lstrip": true,
303
- "normalized": true,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": true
307
- },
308
- "32033": {
309
- "content": "<extra_id_66>",
310
- "lstrip": true,
311
- "normalized": true,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": true
315
- },
316
- "32034": {
317
- "content": "<extra_id_65>",
318
- "lstrip": true,
319
- "normalized": true,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": true
323
- },
324
- "32035": {
325
- "content": "<extra_id_64>",
326
- "lstrip": true,
327
- "normalized": true,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": true
331
- },
332
- "32036": {
333
- "content": "<extra_id_63>",
334
- "lstrip": true,
335
- "normalized": true,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": true
339
- },
340
- "32037": {
341
- "content": "<extra_id_62>",
342
- "lstrip": true,
343
- "normalized": true,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": true
347
- },
348
- "32038": {
349
- "content": "<extra_id_61>",
350
- "lstrip": true,
351
- "normalized": true,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": true
355
- },
356
- "32039": {
357
- "content": "<extra_id_60>",
358
- "lstrip": true,
359
- "normalized": true,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": true
363
- },
364
- "32040": {
365
- "content": "<extra_id_59>",
366
- "lstrip": true,
367
- "normalized": true,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": true
371
- },
372
- "32041": {
373
- "content": "<extra_id_58>",
374
- "lstrip": true,
375
- "normalized": true,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": true
379
- },
380
- "32042": {
381
- "content": "<extra_id_57>",
382
- "lstrip": true,
383
- "normalized": true,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": true
387
- },
388
- "32043": {
389
- "content": "<extra_id_56>",
390
- "lstrip": true,
391
- "normalized": true,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": true
395
- },
396
- "32044": {
397
- "content": "<extra_id_55>",
398
- "lstrip": true,
399
- "normalized": true,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": true
403
- },
404
- "32045": {
405
- "content": "<extra_id_54>",
406
- "lstrip": true,
407
- "normalized": true,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": true
411
- },
412
- "32046": {
413
- "content": "<extra_id_53>",
414
- "lstrip": true,
415
- "normalized": true,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": true
419
- },
420
- "32047": {
421
- "content": "<extra_id_52>",
422
- "lstrip": true,
423
- "normalized": true,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": true
427
- },
428
- "32048": {
429
- "content": "<extra_id_51>",
430
- "lstrip": true,
431
- "normalized": true,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": true
435
- },
436
- "32049": {
437
- "content": "<extra_id_50>",
438
- "lstrip": true,
439
- "normalized": true,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": true
443
- },
444
- "32050": {
445
- "content": "<extra_id_49>",
446
- "lstrip": true,
447
- "normalized": true,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": true
451
- },
452
- "32051": {
453
- "content": "<extra_id_48>",
454
- "lstrip": true,
455
- "normalized": true,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": true
459
- },
460
- "32052": {
461
- "content": "<extra_id_47>",
462
- "lstrip": true,
463
- "normalized": true,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": true
467
- },
468
- "32053": {
469
- "content": "<extra_id_46>",
470
- "lstrip": true,
471
- "normalized": true,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": true
475
- },
476
- "32054": {
477
- "content": "<extra_id_45>",
478
- "lstrip": true,
479
- "normalized": true,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": true
483
- },
484
- "32055": {
485
- "content": "<extra_id_44>",
486
- "lstrip": true,
487
- "normalized": true,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": true
491
- },
492
- "32056": {
493
- "content": "<extra_id_43>",
494
- "lstrip": true,
495
- "normalized": true,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": true
499
- },
500
- "32057": {
501
- "content": "<extra_id_42>",
502
- "lstrip": true,
503
- "normalized": true,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": true
507
- },
508
- "32058": {
509
- "content": "<extra_id_41>",
510
- "lstrip": true,
511
- "normalized": true,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": true
515
- },
516
- "32059": {
517
- "content": "<extra_id_40>",
518
- "lstrip": true,
519
- "normalized": true,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": true
523
- },
524
- "32060": {
525
- "content": "<extra_id_39>",
526
- "lstrip": true,
527
- "normalized": true,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": true
531
- },
532
- "32061": {
533
- "content": "<extra_id_38>",
534
- "lstrip": true,
535
- "normalized": true,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": true
539
- },
540
- "32062": {
541
- "content": "<extra_id_37>",
542
- "lstrip": true,
543
- "normalized": true,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": true
547
- },
548
- "32063": {
549
- "content": "<extra_id_36>",
550
- "lstrip": true,
551
- "normalized": true,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": true
555
- },
556
- "32064": {
557
- "content": "<extra_id_35>",
558
- "lstrip": true,
559
- "normalized": true,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": true
563
- },
564
- "32065": {
565
- "content": "<extra_id_34>",
566
- "lstrip": true,
567
- "normalized": true,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": true
571
- },
572
- "32066": {
573
- "content": "<extra_id_33>",
574
- "lstrip": true,
575
- "normalized": true,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": true
579
- },
580
- "32067": {
581
- "content": "<extra_id_32>",
582
- "lstrip": true,
583
- "normalized": true,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": true
587
- },
588
- "32068": {
589
- "content": "<extra_id_31>",
590
- "lstrip": true,
591
- "normalized": true,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": true
595
- },
596
- "32069": {
597
- "content": "<extra_id_30>",
598
- "lstrip": true,
599
- "normalized": true,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": true
603
- },
604
- "32070": {
605
- "content": "<extra_id_29>",
606
- "lstrip": true,
607
- "normalized": true,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": true
611
- },
612
- "32071": {
613
- "content": "<extra_id_28>",
614
- "lstrip": true,
615
- "normalized": true,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": true
619
- },
620
- "32072": {
621
- "content": "<extra_id_27>",
622
- "lstrip": true,
623
- "normalized": true,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": true
627
- },
628
- "32073": {
629
- "content": "<extra_id_26>",
630
- "lstrip": true,
631
- "normalized": true,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": true
635
- },
636
- "32074": {
637
- "content": "<extra_id_25>",
638
- "lstrip": true,
639
- "normalized": true,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": true
643
- },
644
- "32075": {
645
- "content": "<extra_id_24>",
646
- "lstrip": true,
647
- "normalized": true,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": true
651
- },
652
- "32076": {
653
- "content": "<extra_id_23>",
654
- "lstrip": true,
655
- "normalized": true,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": true
659
- },
660
- "32077": {
661
- "content": "<extra_id_22>",
662
- "lstrip": true,
663
- "normalized": true,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": true
667
- },
668
- "32078": {
669
- "content": "<extra_id_21>",
670
- "lstrip": true,
671
- "normalized": true,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": true
675
- },
676
- "32079": {
677
- "content": "<extra_id_20>",
678
- "lstrip": true,
679
- "normalized": true,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": true
683
- },
684
- "32080": {
685
- "content": "<extra_id_19>",
686
- "lstrip": true,
687
- "normalized": true,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": true
691
- },
692
- "32081": {
693
- "content": "<extra_id_18>",
694
- "lstrip": true,
695
- "normalized": true,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": true
699
- },
700
- "32082": {
701
- "content": "<extra_id_17>",
702
- "lstrip": true,
703
- "normalized": true,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": true
707
- },
708
- "32083": {
709
- "content": "<extra_id_16>",
710
- "lstrip": true,
711
- "normalized": true,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": true
715
- },
716
- "32084": {
717
- "content": "<extra_id_15>",
718
- "lstrip": true,
719
- "normalized": true,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": true
723
- },
724
- "32085": {
725
- "content": "<extra_id_14>",
726
- "lstrip": true,
727
- "normalized": true,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": true
731
- },
732
- "32086": {
733
- "content": "<extra_id_13>",
734
- "lstrip": true,
735
- "normalized": true,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": true
739
- },
740
- "32087": {
741
- "content": "<extra_id_12>",
742
- "lstrip": true,
743
- "normalized": true,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": true
747
- },
748
- "32088": {
749
- "content": "<extra_id_11>",
750
- "lstrip": true,
751
- "normalized": true,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": true
755
- },
756
- "32089": {
757
- "content": "<extra_id_10>",
758
- "lstrip": true,
759
- "normalized": true,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": true
763
- },
764
- "32090": {
765
- "content": "<extra_id_9>",
766
- "lstrip": true,
767
- "normalized": true,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": true
771
- },
772
- "32091": {
773
- "content": "<extra_id_8>",
774
- "lstrip": true,
775
- "normalized": true,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": true
779
- },
780
- "32092": {
781
- "content": "<extra_id_7>",
782
- "lstrip": true,
783
- "normalized": true,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": true
787
- },
788
- "32093": {
789
- "content": "<extra_id_6>",
790
- "lstrip": true,
791
- "normalized": true,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": true
795
- },
796
- "32094": {
797
- "content": "<extra_id_5>",
798
- "lstrip": true,
799
- "normalized": true,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": true
803
- },
804
- "32095": {
805
- "content": "<extra_id_4>",
806
- "lstrip": true,
807
- "normalized": true,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": true
811
- },
812
- "32096": {
813
- "content": "<extra_id_3>",
814
- "lstrip": true,
815
- "normalized": true,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": true
819
- },
820
- "32097": {
821
- "content": "<extra_id_2>",
822
- "lstrip": true,
823
- "normalized": true,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": true
827
- },
828
- "32098": {
829
- "content": "<extra_id_1>",
830
- "lstrip": true,
831
- "normalized": true,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": true
835
- },
836
- "32099": {
837
- "content": "<extra_id_0>",
838
- "lstrip": true,
839
- "normalized": true,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": true
843
- }
844
- },
845
- "additional_special_tokens": [
846
- "<extra_id_99>",
847
- "<extra_id_98>",
848
- "<extra_id_97>",
849
- "<extra_id_96>",
850
- "<extra_id_95>",
851
- "<extra_id_94>",
852
- "<extra_id_93>",
853
- "<extra_id_92>",
854
- "<extra_id_91>",
855
- "<extra_id_90>",
856
- "<extra_id_89>",
857
- "<extra_id_88>",
858
- "<extra_id_87>",
859
- "<extra_id_86>",
860
- "<extra_id_85>",
861
- "<extra_id_84>",
862
- "<extra_id_83>",
863
- "<extra_id_82>",
864
- "<extra_id_81>",
865
- "<extra_id_80>",
866
- "<extra_id_79>",
867
- "<extra_id_78>",
868
- "<extra_id_77>",
869
- "<extra_id_76>",
870
- "<extra_id_75>",
871
- "<extra_id_74>",
872
- "<extra_id_73>",
873
- "<extra_id_72>",
874
- "<extra_id_71>",
875
- "<extra_id_70>",
876
- "<extra_id_69>",
877
- "<extra_id_68>",
878
- "<extra_id_67>",
879
- "<extra_id_66>",
880
- "<extra_id_65>",
881
- "<extra_id_64>",
882
- "<extra_id_63>",
883
- "<extra_id_62>",
884
- "<extra_id_61>",
885
- "<extra_id_60>",
886
- "<extra_id_59>",
887
- "<extra_id_58>",
888
- "<extra_id_57>",
889
- "<extra_id_56>",
890
- "<extra_id_55>",
891
- "<extra_id_54>",
892
- "<extra_id_53>",
893
- "<extra_id_52>",
894
- "<extra_id_51>",
895
- "<extra_id_50>",
896
- "<extra_id_49>",
897
- "<extra_id_48>",
898
- "<extra_id_47>",
899
- "<extra_id_46>",
900
- "<extra_id_45>",
901
- "<extra_id_44>",
902
- "<extra_id_43>",
903
- "<extra_id_42>",
904
- "<extra_id_41>",
905
- "<extra_id_40>",
906
- "<extra_id_39>",
907
- "<extra_id_38>",
908
- "<extra_id_37>",
909
- "<extra_id_36>",
910
- "<extra_id_35>",
911
- "<extra_id_34>",
912
- "<extra_id_33>",
913
- "<extra_id_32>",
914
- "<extra_id_31>",
915
- "<extra_id_30>",
916
- "<extra_id_29>",
917
- "<extra_id_28>",
918
- "<extra_id_27>",
919
- "<extra_id_26>",
920
- "<extra_id_25>",
921
- "<extra_id_24>",
922
- "<extra_id_23>",
923
- "<extra_id_22>",
924
- "<extra_id_21>",
925
- "<extra_id_20>",
926
- "<extra_id_19>",
927
- "<extra_id_18>",
928
- "<extra_id_17>",
929
- "<extra_id_16>",
930
- "<extra_id_15>",
931
- "<extra_id_14>",
932
- "<extra_id_13>",
933
- "<extra_id_12>",
934
- "<extra_id_11>",
935
- "<extra_id_10>",
936
- "<extra_id_9>",
937
- "<extra_id_8>",
938
- "<extra_id_7>",
939
- "<extra_id_6>",
940
- "<extra_id_5>",
941
- "<extra_id_4>",
942
- "<extra_id_3>",
943
- "<extra_id_2>",
944
- "<extra_id_1>",
945
- "<extra_id_0>"
946
- ],
947
- "bos_token": "<s>",
948
- "clean_up_tokenization_spaces": false,
949
- "cls_token": "<s>",
950
- "eos_token": "</s>",
951
- "errors": "replace",
952
- "mask_token": "<mask>",
953
- "model_max_length": 512,
954
- "pad_token": "<pad>",
955
- "sep_token": "</s>",
956
- "tokenizer_class": "RobertaTokenizer",
957
- "trim_offsets": true,
958
- "unk_token": "<unk>"
959
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
+ "lstrip": true,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<extra_id_99>",
847
+ "<extra_id_98>",
848
+ "<extra_id_97>",
849
+ "<extra_id_96>",
850
+ "<extra_id_95>",
851
+ "<extra_id_94>",
852
+ "<extra_id_93>",
853
+ "<extra_id_92>",
854
+ "<extra_id_91>",
855
+ "<extra_id_90>",
856
+ "<extra_id_89>",
857
+ "<extra_id_88>",
858
+ "<extra_id_87>",
859
+ "<extra_id_86>",
860
+ "<extra_id_85>",
861
+ "<extra_id_84>",
862
+ "<extra_id_83>",
863
+ "<extra_id_82>",
864
+ "<extra_id_81>",
865
+ "<extra_id_80>",
866
+ "<extra_id_79>",
867
+ "<extra_id_78>",
868
+ "<extra_id_77>",
869
+ "<extra_id_76>",
870
+ "<extra_id_75>",
871
+ "<extra_id_74>",
872
+ "<extra_id_73>",
873
+ "<extra_id_72>",
874
+ "<extra_id_71>",
875
+ "<extra_id_70>",
876
+ "<extra_id_69>",
877
+ "<extra_id_68>",
878
+ "<extra_id_67>",
879
+ "<extra_id_66>",
880
+ "<extra_id_65>",
881
+ "<extra_id_64>",
882
+ "<extra_id_63>",
883
+ "<extra_id_62>",
884
+ "<extra_id_61>",
885
+ "<extra_id_60>",
886
+ "<extra_id_59>",
887
+ "<extra_id_58>",
888
+ "<extra_id_57>",
889
+ "<extra_id_56>",
890
+ "<extra_id_55>",
891
+ "<extra_id_54>",
892
+ "<extra_id_53>",
893
+ "<extra_id_52>",
894
+ "<extra_id_51>",
895
+ "<extra_id_50>",
896
+ "<extra_id_49>",
897
+ "<extra_id_48>",
898
+ "<extra_id_47>",
899
+ "<extra_id_46>",
900
+ "<extra_id_45>",
901
+ "<extra_id_44>",
902
+ "<extra_id_43>",
903
+ "<extra_id_42>",
904
+ "<extra_id_41>",
905
+ "<extra_id_40>",
906
+ "<extra_id_39>",
907
+ "<extra_id_38>",
908
+ "<extra_id_37>",
909
+ "<extra_id_36>",
910
+ "<extra_id_35>",
911
+ "<extra_id_34>",
912
+ "<extra_id_33>",
913
+ "<extra_id_32>",
914
+ "<extra_id_31>",
915
+ "<extra_id_30>",
916
+ "<extra_id_29>",
917
+ "<extra_id_28>",
918
+ "<extra_id_27>",
919
+ "<extra_id_26>",
920
+ "<extra_id_25>",
921
+ "<extra_id_24>",
922
+ "<extra_id_23>",
923
+ "<extra_id_22>",
924
+ "<extra_id_21>",
925
+ "<extra_id_20>",
926
+ "<extra_id_19>",
927
+ "<extra_id_18>",
928
+ "<extra_id_17>",
929
+ "<extra_id_16>",
930
+ "<extra_id_15>",
931
+ "<extra_id_14>",
932
+ "<extra_id_13>",
933
+ "<extra_id_12>",
934
+ "<extra_id_11>",
935
+ "<extra_id_10>",
936
+ "<extra_id_9>",
937
+ "<extra_id_8>",
938
+ "<extra_id_7>",
939
+ "<extra_id_6>",
940
+ "<extra_id_5>",
941
+ "<extra_id_4>",
942
+ "<extra_id_3>",
943
+ "<extra_id_2>",
944
+ "<extra_id_1>",
945
+ "<extra_id_0>"
946
+ ],
947
+ "bos_token": "<s>",
948
+ "clean_up_tokenization_spaces": false,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "mask_token": "<mask>",
953
+ "model_max_length": 512,
954
+ "pad_token": "<pad>",
955
+ "sep_token": "</s>",
956
+ "tokenizer_class": "RobertaTokenizer",
957
+ "trim_offsets": true,
958
+ "unk_token": "<unk>"
959
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff