Xenova HF Staff commited on
Commit
0d15def
·
verified ·
1 Parent(s): 4c3048c

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +51 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +951 -0
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,951 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "|||IP_ADDRESS|||",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "|||EMAIL_ADDRESS|||",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
+ "content": "|||PHONE_NUMBER|||",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "50279": {
223
+ "content": "<|endoftext|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "50280": {
231
+ "content": "[UNK]",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "50281": {
239
+ "content": "[CLS]",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "50282": {
247
+ "content": "[SEP]",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "50283": {
255
+ "content": "[PAD]",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "50284": {
263
+ "content": "[MASK]",
264
+ "lstrip": true,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "50285": {
271
+ "content": "[unused0]",
272
+ "lstrip": false,
273
+ "normalized": true,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "50286": {
279
+ "content": "[unused1]",
280
+ "lstrip": false,
281
+ "normalized": true,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "50287": {
287
+ "content": "[unused2]",
288
+ "lstrip": false,
289
+ "normalized": true,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "50288": {
295
+ "content": "[unused3]",
296
+ "lstrip": false,
297
+ "normalized": true,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ },
302
+ "50289": {
303
+ "content": "[unused4]",
304
+ "lstrip": false,
305
+ "normalized": true,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false
309
+ },
310
+ "50290": {
311
+ "content": "[unused5]",
312
+ "lstrip": false,
313
+ "normalized": true,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": false
317
+ },
318
+ "50291": {
319
+ "content": "[unused6]",
320
+ "lstrip": false,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": false
325
+ },
326
+ "50292": {
327
+ "content": "[unused7]",
328
+ "lstrip": false,
329
+ "normalized": true,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": false
333
+ },
334
+ "50293": {
335
+ "content": "[unused8]",
336
+ "lstrip": false,
337
+ "normalized": true,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": false
341
+ },
342
+ "50294": {
343
+ "content": "[unused9]",
344
+ "lstrip": false,
345
+ "normalized": true,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": false
349
+ },
350
+ "50295": {
351
+ "content": "[unused10]",
352
+ "lstrip": false,
353
+ "normalized": true,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": false
357
+ },
358
+ "50296": {
359
+ "content": "[unused11]",
360
+ "lstrip": false,
361
+ "normalized": true,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": false
365
+ },
366
+ "50297": {
367
+ "content": "[unused12]",
368
+ "lstrip": false,
369
+ "normalized": true,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": false
373
+ },
374
+ "50298": {
375
+ "content": "[unused13]",
376
+ "lstrip": false,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": false
381
+ },
382
+ "50299": {
383
+ "content": "[unused14]",
384
+ "lstrip": false,
385
+ "normalized": true,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": false
389
+ },
390
+ "50300": {
391
+ "content": "[unused15]",
392
+ "lstrip": false,
393
+ "normalized": true,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": false
397
+ },
398
+ "50301": {
399
+ "content": "[unused16]",
400
+ "lstrip": false,
401
+ "normalized": true,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": false
405
+ },
406
+ "50302": {
407
+ "content": "[unused17]",
408
+ "lstrip": false,
409
+ "normalized": true,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": false
413
+ },
414
+ "50303": {
415
+ "content": "[unused18]",
416
+ "lstrip": false,
417
+ "normalized": true,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": false
421
+ },
422
+ "50304": {
423
+ "content": "[unused19]",
424
+ "lstrip": false,
425
+ "normalized": true,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": false
429
+ },
430
+ "50305": {
431
+ "content": "[unused20]",
432
+ "lstrip": false,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": false
437
+ },
438
+ "50306": {
439
+ "content": "[unused21]",
440
+ "lstrip": false,
441
+ "normalized": true,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": false
445
+ },
446
+ "50307": {
447
+ "content": "[unused22]",
448
+ "lstrip": false,
449
+ "normalized": true,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": false
453
+ },
454
+ "50308": {
455
+ "content": "[unused23]",
456
+ "lstrip": false,
457
+ "normalized": true,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": false
461
+ },
462
+ "50309": {
463
+ "content": "[unused24]",
464
+ "lstrip": false,
465
+ "normalized": true,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": false
469
+ },
470
+ "50310": {
471
+ "content": "[unused25]",
472
+ "lstrip": false,
473
+ "normalized": true,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": false
477
+ },
478
+ "50311": {
479
+ "content": "[unused26]",
480
+ "lstrip": false,
481
+ "normalized": true,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": false
485
+ },
486
+ "50312": {
487
+ "content": "[unused27]",
488
+ "lstrip": false,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": false
493
+ },
494
+ "50313": {
495
+ "content": "[unused28]",
496
+ "lstrip": false,
497
+ "normalized": true,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": false
501
+ },
502
+ "50314": {
503
+ "content": "[unused29]",
504
+ "lstrip": false,
505
+ "normalized": true,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": false
509
+ },
510
+ "50315": {
511
+ "content": "[unused30]",
512
+ "lstrip": false,
513
+ "normalized": true,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": false
517
+ },
518
+ "50316": {
519
+ "content": "[unused31]",
520
+ "lstrip": false,
521
+ "normalized": true,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": false
525
+ },
526
+ "50317": {
527
+ "content": "[unused32]",
528
+ "lstrip": false,
529
+ "normalized": true,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": false
533
+ },
534
+ "50318": {
535
+ "content": "[unused33]",
536
+ "lstrip": false,
537
+ "normalized": true,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": false
541
+ },
542
+ "50319": {
543
+ "content": "[unused34]",
544
+ "lstrip": false,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": false
549
+ },
550
+ "50320": {
551
+ "content": "[unused35]",
552
+ "lstrip": false,
553
+ "normalized": true,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": false
557
+ },
558
+ "50321": {
559
+ "content": "[unused36]",
560
+ "lstrip": false,
561
+ "normalized": true,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": false
565
+ },
566
+ "50322": {
567
+ "content": "[unused37]",
568
+ "lstrip": false,
569
+ "normalized": true,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": false
573
+ },
574
+ "50323": {
575
+ "content": "[unused38]",
576
+ "lstrip": false,
577
+ "normalized": true,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": false
581
+ },
582
+ "50324": {
583
+ "content": "[unused39]",
584
+ "lstrip": false,
585
+ "normalized": true,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": false
589
+ },
590
+ "50325": {
591
+ "content": "[unused40]",
592
+ "lstrip": false,
593
+ "normalized": true,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": false
597
+ },
598
+ "50326": {
599
+ "content": "[unused41]",
600
+ "lstrip": false,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": false
605
+ },
606
+ "50327": {
607
+ "content": "[unused42]",
608
+ "lstrip": false,
609
+ "normalized": true,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": false
613
+ },
614
+ "50328": {
615
+ "content": "[unused43]",
616
+ "lstrip": false,
617
+ "normalized": true,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": false
621
+ },
622
+ "50329": {
623
+ "content": "[unused44]",
624
+ "lstrip": false,
625
+ "normalized": true,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": false
629
+ },
630
+ "50330": {
631
+ "content": "[unused45]",
632
+ "lstrip": false,
633
+ "normalized": true,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": false
637
+ },
638
+ "50331": {
639
+ "content": "[unused46]",
640
+ "lstrip": false,
641
+ "normalized": true,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": false
645
+ },
646
+ "50332": {
647
+ "content": "[unused47]",
648
+ "lstrip": false,
649
+ "normalized": true,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": false
653
+ },
654
+ "50333": {
655
+ "content": "[unused48]",
656
+ "lstrip": false,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": false
661
+ },
662
+ "50334": {
663
+ "content": "[unused49]",
664
+ "lstrip": false,
665
+ "normalized": true,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": false
669
+ },
670
+ "50335": {
671
+ "content": "[unused50]",
672
+ "lstrip": false,
673
+ "normalized": true,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": false
677
+ },
678
+ "50336": {
679
+ "content": "[unused51]",
680
+ "lstrip": false,
681
+ "normalized": true,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": false
685
+ },
686
+ "50337": {
687
+ "content": "[unused52]",
688
+ "lstrip": false,
689
+ "normalized": true,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": false
693
+ },
694
+ "50338": {
695
+ "content": "[unused53]",
696
+ "lstrip": false,
697
+ "normalized": true,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": false
701
+ },
702
+ "50339": {
703
+ "content": "[unused54]",
704
+ "lstrip": false,
705
+ "normalized": true,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": false
709
+ },
710
+ "50340": {
711
+ "content": "[unused55]",
712
+ "lstrip": false,
713
+ "normalized": true,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": false
717
+ },
718
+ "50341": {
719
+ "content": "[unused56]",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": false
725
+ },
726
+ "50342": {
727
+ "content": "[unused57]",
728
+ "lstrip": false,
729
+ "normalized": true,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": false
733
+ },
734
+ "50343": {
735
+ "content": "[unused58]",
736
+ "lstrip": false,
737
+ "normalized": true,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": false
741
+ },
742
+ "50344": {
743
+ "content": "[unused59]",
744
+ "lstrip": false,
745
+ "normalized": true,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": false
749
+ },
750
+ "50345": {
751
+ "content": "[unused60]",
752
+ "lstrip": false,
753
+ "normalized": true,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": false
757
+ },
758
+ "50346": {
759
+ "content": "[unused61]",
760
+ "lstrip": false,
761
+ "normalized": true,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": false
765
+ },
766
+ "50347": {
767
+ "content": "[unused62]",
768
+ "lstrip": false,
769
+ "normalized": true,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": false
773
+ },
774
+ "50348": {
775
+ "content": "[unused63]",
776
+ "lstrip": false,
777
+ "normalized": true,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": false
781
+ },
782
+ "50349": {
783
+ "content": "[unused64]",
784
+ "lstrip": false,
785
+ "normalized": true,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": false
789
+ },
790
+ "50350": {
791
+ "content": "[unused65]",
792
+ "lstrip": false,
793
+ "normalized": true,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": false
797
+ },
798
+ "50351": {
799
+ "content": "[unused66]",
800
+ "lstrip": false,
801
+ "normalized": true,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": false
805
+ },
806
+ "50352": {
807
+ "content": "[unused67]",
808
+ "lstrip": false,
809
+ "normalized": true,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": false
813
+ },
814
+ "50353": {
815
+ "content": "[unused68]",
816
+ "lstrip": false,
817
+ "normalized": true,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": false
821
+ },
822
+ "50354": {
823
+ "content": "[unused69]",
824
+ "lstrip": false,
825
+ "normalized": true,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": false
829
+ },
830
+ "50355": {
831
+ "content": "[unused70]",
832
+ "lstrip": false,
833
+ "normalized": true,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": false
837
+ },
838
+ "50356": {
839
+ "content": "[unused71]",
840
+ "lstrip": false,
841
+ "normalized": true,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": false
845
+ },
846
+ "50357": {
847
+ "content": "[unused72]",
848
+ "lstrip": false,
849
+ "normalized": true,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": false
853
+ },
854
+ "50358": {
855
+ "content": "[unused73]",
856
+ "lstrip": false,
857
+ "normalized": true,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": false
861
+ },
862
+ "50359": {
863
+ "content": "[unused74]",
864
+ "lstrip": false,
865
+ "normalized": true,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": false
869
+ },
870
+ "50360": {
871
+ "content": "[unused75]",
872
+ "lstrip": false,
873
+ "normalized": true,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": false
877
+ },
878
+ "50361": {
879
+ "content": "[unused76]",
880
+ "lstrip": false,
881
+ "normalized": true,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": false
885
+ },
886
+ "50362": {
887
+ "content": "[unused77]",
888
+ "lstrip": false,
889
+ "normalized": true,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": false
893
+ },
894
+ "50363": {
895
+ "content": "[unused78]",
896
+ "lstrip": false,
897
+ "normalized": true,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": false
901
+ },
902
+ "50364": {
903
+ "content": "[unused79]",
904
+ "lstrip": false,
905
+ "normalized": true,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": false
909
+ },
910
+ "50365": {
911
+ "content": "[unused80]",
912
+ "lstrip": false,
913
+ "normalized": true,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": false
917
+ },
918
+ "50366": {
919
+ "content": "[unused81]",
920
+ "lstrip": false,
921
+ "normalized": true,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": false
925
+ },
926
+ "50367": {
927
+ "content": "[unused82]",
928
+ "lstrip": false,
929
+ "normalized": true,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": false
933
+ }
934
+ },
935
+ "bos_token": "[CLS]",
936
+ "clean_up_tokenization_spaces": true,
937
+ "cls_token": "[CLS]",
938
+ "eos_token": "[SEP]",
939
+ "extra_special_tokens": {},
940
+ "is_causal": true,
941
+ "mask_token": "[MASK]",
942
+ "model_input_names": [
943
+ "input_ids",
944
+ "attention_mask"
945
+ ],
946
+ "model_max_length": 7999,
947
+ "pad_token": "[PAD]",
948
+ "sep_token": "[SEP]",
949
+ "tokenizer_class": "GPTNeoXTokenizer",
950
+ "unk_token": "[UNK]"
951
+ }