ehristoforu commited on
Commit
caeea62
1 Parent(s): 4a97570

Upload 4 files

Browse files
tokenizer_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json CHANGED
@@ -1,122 +1,27 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
  "eos_token": {
105
- "content": "</s>",
106
  "lstrip": false,
107
  "normalized": false,
108
  "rstrip": false,
109
  "single_word": false
110
  },
111
  "pad_token": {
112
- "content": "<pad>",
113
  "lstrip": false,
114
  "normalized": false,
115
  "rstrip": false,
116
  "single_word": false
117
  },
118
  "unk_token": {
119
- "content": "<unk>",
120
  "lstrip": false,
121
  "normalized": false,
122
  "rstrip": false,
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "!",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "unk_token": {
24
+ "content": "<|endoftext|>",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
tokenizer_2/tokenizer_config.json CHANGED
@@ -1,940 +1,38 @@
1
  {
2
- "add_prefix_space": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<unk>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "32000": {
29
- "content": "<extra_id_99>",
30
- "lstrip": true,
31
- "normalized": false,
32
- "rstrip": true,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "32001": {
37
- "content": "<extra_id_98>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": true,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "32002": {
45
- "content": "<extra_id_97>",
46
- "lstrip": true,
47
- "normalized": false,
48
- "rstrip": true,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "32003": {
53
- "content": "<extra_id_96>",
54
- "lstrip": true,
55
- "normalized": false,
56
- "rstrip": true,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "32004": {
61
- "content": "<extra_id_95>",
62
- "lstrip": true,
63
- "normalized": false,
64
- "rstrip": true,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "32005": {
69
- "content": "<extra_id_94>",
70
- "lstrip": true,
71
- "normalized": false,
72
- "rstrip": true,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "32006": {
77
- "content": "<extra_id_93>",
78
- "lstrip": true,
79
- "normalized": false,
80
- "rstrip": true,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "32007": {
85
- "content": "<extra_id_92>",
86
- "lstrip": true,
87
- "normalized": false,
88
- "rstrip": true,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "32008": {
93
- "content": "<extra_id_91>",
94
- "lstrip": true,
95
- "normalized": false,
96
- "rstrip": true,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "32009": {
101
- "content": "<extra_id_90>",
102
- "lstrip": true,
103
- "normalized": false,
104
- "rstrip": true,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "32010": {
109
- "content": "<extra_id_89>",
110
- "lstrip": true,
111
- "normalized": false,
112
- "rstrip": true,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "32011": {
117
- "content": "<extra_id_88>",
118
- "lstrip": true,
119
- "normalized": false,
120
- "rstrip": true,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "32012": {
125
- "content": "<extra_id_87>",
126
- "lstrip": true,
127
- "normalized": false,
128
- "rstrip": true,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "32013": {
133
- "content": "<extra_id_86>",
134
- "lstrip": true,
135
- "normalized": false,
136
- "rstrip": true,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "32014": {
141
- "content": "<extra_id_85>",
142
- "lstrip": true,
143
- "normalized": false,
144
- "rstrip": true,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "32015": {
149
- "content": "<extra_id_84>",
150
- "lstrip": true,
151
- "normalized": false,
152
- "rstrip": true,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "32016": {
157
- "content": "<extra_id_83>",
158
- "lstrip": true,
159
- "normalized": false,
160
- "rstrip": true,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "32017": {
165
- "content": "<extra_id_82>",
166
- "lstrip": true,
167
- "normalized": false,
168
- "rstrip": true,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "32018": {
173
- "content": "<extra_id_81>",
174
- "lstrip": true,
175
- "normalized": false,
176
- "rstrip": true,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "32019": {
181
- "content": "<extra_id_80>",
182
- "lstrip": true,
183
- "normalized": false,
184
- "rstrip": true,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "32020": {
189
- "content": "<extra_id_79>",
190
- "lstrip": true,
191
- "normalized": false,
192
- "rstrip": true,
193
- "single_word": false,
194
- "special": true
195
- },
196
- "32021": {
197
- "content": "<extra_id_78>",
198
- "lstrip": true,
199
- "normalized": false,
200
- "rstrip": true,
201
- "single_word": false,
202
- "special": true
203
- },
204
- "32022": {
205
- "content": "<extra_id_77>",
206
- "lstrip": true,
207
- "normalized": false,
208
- "rstrip": true,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "32023": {
213
- "content": "<extra_id_76>",
214
- "lstrip": true,
215
- "normalized": false,
216
- "rstrip": true,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "32024": {
221
- "content": "<extra_id_75>",
222
- "lstrip": true,
223
- "normalized": false,
224
- "rstrip": true,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "32025": {
229
- "content": "<extra_id_74>",
230
- "lstrip": true,
231
- "normalized": false,
232
- "rstrip": true,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "32026": {
237
- "content": "<extra_id_73>",
238
- "lstrip": true,
239
- "normalized": false,
240
- "rstrip": true,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "32027": {
245
- "content": "<extra_id_72>",
246
- "lstrip": true,
247
- "normalized": false,
248
- "rstrip": true,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "32028": {
253
- "content": "<extra_id_71>",
254
- "lstrip": true,
255
- "normalized": false,
256
- "rstrip": true,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "32029": {
261
- "content": "<extra_id_70>",
262
- "lstrip": true,
263
- "normalized": false,
264
- "rstrip": true,
265
- "single_word": false,
266
- "special": true
267
- },
268
- "32030": {
269
- "content": "<extra_id_69>",
270
- "lstrip": true,
271
- "normalized": false,
272
- "rstrip": true,
273
- "single_word": false,
274
- "special": true
275
- },
276
- "32031": {
277
- "content": "<extra_id_68>",
278
- "lstrip": true,
279
- "normalized": false,
280
- "rstrip": true,
281
- "single_word": false,
282
- "special": true
283
- },
284
- "32032": {
285
- "content": "<extra_id_67>",
286
- "lstrip": true,
287
- "normalized": false,
288
- "rstrip": true,
289
- "single_word": false,
290
- "special": true
291
- },
292
- "32033": {
293
- "content": "<extra_id_66>",
294
- "lstrip": true,
295
- "normalized": false,
296
- "rstrip": true,
297
- "single_word": false,
298
- "special": true
299
- },
300
- "32034": {
301
- "content": "<extra_id_65>",
302
- "lstrip": true,
303
- "normalized": false,
304
- "rstrip": true,
305
- "single_word": false,
306
- "special": true
307
- },
308
- "32035": {
309
- "content": "<extra_id_64>",
310
- "lstrip": true,
311
- "normalized": false,
312
- "rstrip": true,
313
- "single_word": false,
314
- "special": true
315
- },
316
- "32036": {
317
- "content": "<extra_id_63>",
318
- "lstrip": true,
319
- "normalized": false,
320
- "rstrip": true,
321
- "single_word": false,
322
- "special": true
323
- },
324
- "32037": {
325
- "content": "<extra_id_62>",
326
- "lstrip": true,
327
- "normalized": false,
328
- "rstrip": true,
329
- "single_word": false,
330
- "special": true
331
- },
332
- "32038": {
333
- "content": "<extra_id_61>",
334
- "lstrip": true,
335
- "normalized": false,
336
- "rstrip": true,
337
- "single_word": false,
338
- "special": true
339
- },
340
- "32039": {
341
- "content": "<extra_id_60>",
342
- "lstrip": true,
343
- "normalized": false,
344
- "rstrip": true,
345
- "single_word": false,
346
- "special": true
347
- },
348
- "32040": {
349
- "content": "<extra_id_59>",
350
- "lstrip": true,
351
- "normalized": false,
352
- "rstrip": true,
353
- "single_word": false,
354
- "special": true
355
- },
356
- "32041": {
357
- "content": "<extra_id_58>",
358
- "lstrip": true,
359
- "normalized": false,
360
- "rstrip": true,
361
- "single_word": false,
362
- "special": true
363
- },
364
- "32042": {
365
- "content": "<extra_id_57>",
366
- "lstrip": true,
367
- "normalized": false,
368
- "rstrip": true,
369
- "single_word": false,
370
- "special": true
371
- },
372
- "32043": {
373
- "content": "<extra_id_56>",
374
- "lstrip": true,
375
- "normalized": false,
376
- "rstrip": true,
377
- "single_word": false,
378
- "special": true
379
- },
380
- "32044": {
381
- "content": "<extra_id_55>",
382
- "lstrip": true,
383
- "normalized": false,
384
- "rstrip": true,
385
- "single_word": false,
386
- "special": true
387
- },
388
- "32045": {
389
- "content": "<extra_id_54>",
390
- "lstrip": true,
391
- "normalized": false,
392
- "rstrip": true,
393
- "single_word": false,
394
- "special": true
395
- },
396
- "32046": {
397
- "content": "<extra_id_53>",
398
- "lstrip": true,
399
- "normalized": false,
400
- "rstrip": true,
401
- "single_word": false,
402
- "special": true
403
- },
404
- "32047": {
405
- "content": "<extra_id_52>",
406
- "lstrip": true,
407
- "normalized": false,
408
- "rstrip": true,
409
- "single_word": false,
410
- "special": true
411
- },
412
- "32048": {
413
- "content": "<extra_id_51>",
414
- "lstrip": true,
415
- "normalized": false,
416
- "rstrip": true,
417
- "single_word": false,
418
- "special": true
419
- },
420
- "32049": {
421
- "content": "<extra_id_50>",
422
- "lstrip": true,
423
- "normalized": false,
424
- "rstrip": true,
425
- "single_word": false,
426
- "special": true
427
- },
428
- "32050": {
429
- "content": "<extra_id_49>",
430
- "lstrip": true,
431
- "normalized": false,
432
- "rstrip": true,
433
- "single_word": false,
434
- "special": true
435
- },
436
- "32051": {
437
- "content": "<extra_id_48>",
438
- "lstrip": true,
439
- "normalized": false,
440
- "rstrip": true,
441
- "single_word": false,
442
- "special": true
443
- },
444
- "32052": {
445
- "content": "<extra_id_47>",
446
- "lstrip": true,
447
- "normalized": false,
448
- "rstrip": true,
449
- "single_word": false,
450
- "special": true
451
- },
452
- "32053": {
453
- "content": "<extra_id_46>",
454
- "lstrip": true,
455
- "normalized": false,
456
- "rstrip": true,
457
- "single_word": false,
458
- "special": true
459
- },
460
- "32054": {
461
- "content": "<extra_id_45>",
462
- "lstrip": true,
463
- "normalized": false,
464
- "rstrip": true,
465
- "single_word": false,
466
- "special": true
467
- },
468
- "32055": {
469
- "content": "<extra_id_44>",
470
- "lstrip": true,
471
- "normalized": false,
472
- "rstrip": true,
473
- "single_word": false,
474
- "special": true
475
- },
476
- "32056": {
477
- "content": "<extra_id_43>",
478
- "lstrip": true,
479
- "normalized": false,
480
- "rstrip": true,
481
- "single_word": false,
482
- "special": true
483
- },
484
- "32057": {
485
- "content": "<extra_id_42>",
486
- "lstrip": true,
487
- "normalized": false,
488
- "rstrip": true,
489
- "single_word": false,
490
- "special": true
491
- },
492
- "32058": {
493
- "content": "<extra_id_41>",
494
- "lstrip": true,
495
- "normalized": false,
496
- "rstrip": true,
497
- "single_word": false,
498
- "special": true
499
- },
500
- "32059": {
501
- "content": "<extra_id_40>",
502
- "lstrip": true,
503
- "normalized": false,
504
- "rstrip": true,
505
- "single_word": false,
506
- "special": true
507
- },
508
- "32060": {
509
- "content": "<extra_id_39>",
510
- "lstrip": true,
511
- "normalized": false,
512
- "rstrip": true,
513
- "single_word": false,
514
- "special": true
515
- },
516
- "32061": {
517
- "content": "<extra_id_38>",
518
- "lstrip": true,
519
- "normalized": false,
520
- "rstrip": true,
521
- "single_word": false,
522
- "special": true
523
- },
524
- "32062": {
525
- "content": "<extra_id_37>",
526
- "lstrip": true,
527
- "normalized": false,
528
- "rstrip": true,
529
- "single_word": false,
530
- "special": true
531
- },
532
- "32063": {
533
- "content": "<extra_id_36>",
534
- "lstrip": true,
535
- "normalized": false,
536
- "rstrip": true,
537
- "single_word": false,
538
- "special": true
539
- },
540
- "32064": {
541
- "content": "<extra_id_35>",
542
- "lstrip": true,
543
- "normalized": false,
544
- "rstrip": true,
545
- "single_word": false,
546
- "special": true
547
- },
548
- "32065": {
549
- "content": "<extra_id_34>",
550
- "lstrip": true,
551
- "normalized": false,
552
- "rstrip": true,
553
- "single_word": false,
554
- "special": true
555
- },
556
- "32066": {
557
- "content": "<extra_id_33>",
558
- "lstrip": true,
559
- "normalized": false,
560
- "rstrip": true,
561
- "single_word": false,
562
- "special": true
563
- },
564
- "32067": {
565
- "content": "<extra_id_32>",
566
- "lstrip": true,
567
- "normalized": false,
568
- "rstrip": true,
569
- "single_word": false,
570
- "special": true
571
- },
572
- "32068": {
573
- "content": "<extra_id_31>",
574
- "lstrip": true,
575
- "normalized": false,
576
- "rstrip": true,
577
- "single_word": false,
578
- "special": true
579
- },
580
- "32069": {
581
- "content": "<extra_id_30>",
582
- "lstrip": true,
583
- "normalized": false,
584
- "rstrip": true,
585
- "single_word": false,
586
- "special": true
587
- },
588
- "32070": {
589
- "content": "<extra_id_29>",
590
- "lstrip": true,
591
- "normalized": false,
592
- "rstrip": true,
593
- "single_word": false,
594
- "special": true
595
- },
596
- "32071": {
597
- "content": "<extra_id_28>",
598
- "lstrip": true,
599
- "normalized": false,
600
- "rstrip": true,
601
- "single_word": false,
602
- "special": true
603
- },
604
- "32072": {
605
- "content": "<extra_id_27>",
606
- "lstrip": true,
607
- "normalized": false,
608
- "rstrip": true,
609
- "single_word": false,
610
- "special": true
611
- },
612
- "32073": {
613
- "content": "<extra_id_26>",
614
- "lstrip": true,
615
- "normalized": false,
616
- "rstrip": true,
617
- "single_word": false,
618
- "special": true
619
- },
620
- "32074": {
621
- "content": "<extra_id_25>",
622
- "lstrip": true,
623
- "normalized": false,
624
- "rstrip": true,
625
- "single_word": false,
626
- "special": true
627
- },
628
- "32075": {
629
- "content": "<extra_id_24>",
630
- "lstrip": true,
631
- "normalized": false,
632
- "rstrip": true,
633
- "single_word": false,
634
- "special": true
635
- },
636
- "32076": {
637
- "content": "<extra_id_23>",
638
- "lstrip": true,
639
- "normalized": false,
640
- "rstrip": true,
641
- "single_word": false,
642
- "special": true
643
- },
644
- "32077": {
645
- "content": "<extra_id_22>",
646
- "lstrip": true,
647
- "normalized": false,
648
- "rstrip": true,
649
- "single_word": false,
650
- "special": true
651
- },
652
- "32078": {
653
- "content": "<extra_id_21>",
654
- "lstrip": true,
655
- "normalized": false,
656
- "rstrip": true,
657
- "single_word": false,
658
- "special": true
659
- },
660
- "32079": {
661
- "content": "<extra_id_20>",
662
- "lstrip": true,
663
- "normalized": false,
664
- "rstrip": true,
665
- "single_word": false,
666
- "special": true
667
- },
668
- "32080": {
669
- "content": "<extra_id_19>",
670
- "lstrip": true,
671
- "normalized": false,
672
- "rstrip": true,
673
- "single_word": false,
674
- "special": true
675
- },
676
- "32081": {
677
- "content": "<extra_id_18>",
678
- "lstrip": true,
679
- "normalized": false,
680
- "rstrip": true,
681
- "single_word": false,
682
- "special": true
683
- },
684
- "32082": {
685
- "content": "<extra_id_17>",
686
- "lstrip": true,
687
- "normalized": false,
688
- "rstrip": true,
689
- "single_word": false,
690
- "special": true
691
- },
692
- "32083": {
693
- "content": "<extra_id_16>",
694
- "lstrip": true,
695
- "normalized": false,
696
- "rstrip": true,
697
- "single_word": false,
698
- "special": true
699
- },
700
- "32084": {
701
- "content": "<extra_id_15>",
702
- "lstrip": true,
703
- "normalized": false,
704
- "rstrip": true,
705
- "single_word": false,
706
- "special": true
707
- },
708
- "32085": {
709
- "content": "<extra_id_14>",
710
- "lstrip": true,
711
- "normalized": false,
712
- "rstrip": true,
713
- "single_word": false,
714
- "special": true
715
- },
716
- "32086": {
717
- "content": "<extra_id_13>",
718
- "lstrip": true,
719
- "normalized": false,
720
- "rstrip": true,
721
- "single_word": false,
722
- "special": true
723
- },
724
- "32087": {
725
- "content": "<extra_id_12>",
726
- "lstrip": true,
727
- "normalized": false,
728
- "rstrip": true,
729
- "single_word": false,
730
- "special": true
731
- },
732
- "32088": {
733
- "content": "<extra_id_11>",
734
- "lstrip": true,
735
- "normalized": false,
736
- "rstrip": true,
737
- "single_word": false,
738
- "special": true
739
- },
740
- "32089": {
741
- "content": "<extra_id_10>",
742
- "lstrip": true,
743
- "normalized": false,
744
- "rstrip": true,
745
- "single_word": false,
746
- "special": true
747
- },
748
- "32090": {
749
- "content": "<extra_id_9>",
750
- "lstrip": true,
751
- "normalized": false,
752
- "rstrip": true,
753
- "single_word": false,
754
- "special": true
755
- },
756
- "32091": {
757
- "content": "<extra_id_8>",
758
- "lstrip": true,
759
- "normalized": false,
760
- "rstrip": true,
761
- "single_word": false,
762
- "special": true
763
- },
764
- "32092": {
765
- "content": "<extra_id_7>",
766
- "lstrip": true,
767
- "normalized": false,
768
- "rstrip": true,
769
- "single_word": false,
770
- "special": true
771
- },
772
- "32093": {
773
- "content": "<extra_id_6>",
774
- "lstrip": true,
775
- "normalized": false,
776
- "rstrip": true,
777
- "single_word": false,
778
- "special": true
779
- },
780
- "32094": {
781
- "content": "<extra_id_5>",
782
- "lstrip": true,
783
- "normalized": false,
784
- "rstrip": true,
785
- "single_word": false,
786
- "special": true
787
- },
788
- "32095": {
789
- "content": "<extra_id_4>",
790
- "lstrip": true,
791
- "normalized": false,
792
- "rstrip": true,
793
- "single_word": false,
794
- "special": true
795
- },
796
- "32096": {
797
- "content": "<extra_id_3>",
798
- "lstrip": true,
799
- "normalized": false,
800
- "rstrip": true,
801
- "single_word": false,
802
- "special": true
803
- },
804
- "32097": {
805
- "content": "<extra_id_2>",
806
- "lstrip": true,
807
- "normalized": false,
808
- "rstrip": true,
809
- "single_word": false,
810
- "special": true
811
- },
812
- "32098": {
813
- "content": "<extra_id_1>",
814
- "lstrip": true,
815
- "normalized": false,
816
- "rstrip": true,
817
- "single_word": false,
818
- "special": true
819
- },
820
- "32099": {
821
- "content": "<extra_id_0>",
822
- "lstrip": true,
823
- "normalized": false,
824
- "rstrip": true,
825
- "single_word": false,
826
- "special": true
827
- }
828
- },
829
- "additional_special_tokens": [
830
- "<extra_id_0>",
831
- "<extra_id_1>",
832
- "<extra_id_2>",
833
- "<extra_id_3>",
834
- "<extra_id_4>",
835
- "<extra_id_5>",
836
- "<extra_id_6>",
837
- "<extra_id_7>",
838
- "<extra_id_8>",
839
- "<extra_id_9>",
840
- "<extra_id_10>",
841
- "<extra_id_11>",
842
- "<extra_id_12>",
843
- "<extra_id_13>",
844
- "<extra_id_14>",
845
- "<extra_id_15>",
846
- "<extra_id_16>",
847
- "<extra_id_17>",
848
- "<extra_id_18>",
849
- "<extra_id_19>",
850
- "<extra_id_20>",
851
- "<extra_id_21>",
852
- "<extra_id_22>",
853
- "<extra_id_23>",
854
- "<extra_id_24>",
855
- "<extra_id_25>",
856
- "<extra_id_26>",
857
- "<extra_id_27>",
858
- "<extra_id_28>",
859
- "<extra_id_29>",
860
- "<extra_id_30>",
861
- "<extra_id_31>",
862
- "<extra_id_32>",
863
- "<extra_id_33>",
864
- "<extra_id_34>",
865
- "<extra_id_35>",
866
- "<extra_id_36>",
867
- "<extra_id_37>",
868
- "<extra_id_38>",
869
- "<extra_id_39>",
870
- "<extra_id_40>",
871
- "<extra_id_41>",
872
- "<extra_id_42>",
873
- "<extra_id_43>",
874
- "<extra_id_44>",
875
- "<extra_id_45>",
876
- "<extra_id_46>",
877
- "<extra_id_47>",
878
- "<extra_id_48>",
879
- "<extra_id_49>",
880
- "<extra_id_50>",
881
- "<extra_id_51>",
882
- "<extra_id_52>",
883
- "<extra_id_53>",
884
- "<extra_id_54>",
885
- "<extra_id_55>",
886
- "<extra_id_56>",
887
- "<extra_id_57>",
888
- "<extra_id_58>",
889
- "<extra_id_59>",
890
- "<extra_id_60>",
891
- "<extra_id_61>",
892
- "<extra_id_62>",
893
- "<extra_id_63>",
894
- "<extra_id_64>",
895
- "<extra_id_65>",
896
- "<extra_id_66>",
897
- "<extra_id_67>",
898
- "<extra_id_68>",
899
- "<extra_id_69>",
900
- "<extra_id_70>",
901
- "<extra_id_71>",
902
- "<extra_id_72>",
903
- "<extra_id_73>",
904
- "<extra_id_74>",
905
- "<extra_id_75>",
906
- "<extra_id_76>",
907
- "<extra_id_77>",
908
- "<extra_id_78>",
909
- "<extra_id_79>",
910
- "<extra_id_80>",
911
- "<extra_id_81>",
912
- "<extra_id_82>",
913
- "<extra_id_83>",
914
- "<extra_id_84>",
915
- "<extra_id_85>",
916
- "<extra_id_86>",
917
- "<extra_id_87>",
918
- "<extra_id_88>",
919
- "<extra_id_89>",
920
- "<extra_id_90>",
921
- "<extra_id_91>",
922
- "<extra_id_92>",
923
- "<extra_id_93>",
924
- "<extra_id_94>",
925
- "<extra_id_95>",
926
- "<extra_id_96>",
927
- "<extra_id_97>",
928
- "<extra_id_98>",
929
- "<extra_id_99>"
930
- ],
931
- "clean_up_tokenization_spaces": true,
932
- "eos_token": "</s>",
933
- "extra_ids": 100,
934
- "legacy": true,
935
- "model_max_length": 512,
936
- "pad_token": "<pad>",
937
- "sp_model_kwargs": {},
938
- "tokenizer_class": "T5Tokenizer",
939
- "unk_token": "<unk>"
940
- }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|startoftext|>",
30
+ "clean_up_tokenization_spaces": true,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "model_max_length": 77,
35
+ "pad_token": "!",
36
+ "tokenizer_class": "CLIPTokenizerFast",
37
+ "unk_token": "<|endoftext|>"
38
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff