ayjays132 commited on
Commit
e9d0ddf
·
verified ·
1 Parent(s): b59c7de

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -1
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +73 -667
special_tokens_map.json CHANGED
@@ -3,7 +3,7 @@
3
  "cls_token": "[CLS]",
4
  "eos_token": "[EOS]",
5
  "mask_token": "[MASK]",
6
- "pad_token": "[PAD]",
7
  "sep_token": "[SEP]",
8
  "unk_token": "[UNK]"
9
  }
 
3
  "cls_token": "[CLS]",
4
  "eos_token": "[EOS]",
5
  "mask_token": "[MASK]",
6
+ "pad_token": "[UNK]",
7
  "sep_token": "[SEP]",
8
  "unk_token": "[UNK]"
9
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1c20b7a90d2b5bd165c0532f7f94a9f412f47fe9fca3bb900b0a9cfd95365d1
3
- size 2114555
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f0c62cb71d1012cd005d3d862edc2c52d9650634e6f60581138177e25932f3
3
+ size 2217051
tokenizer_config.json CHANGED
@@ -1,667 +1,73 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "11274": {
5
- "content": "good",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": false
11
- },
12
- "26209": {
13
- "content": "response",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": false
19
- },
20
- "34191": {
21
- "content": "happy",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "38986": {
29
- "content": "environment",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
- "50256": {
37
- "content": "",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "50257": {
45
- "content": "",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "50258": {
53
- "content": "<bos>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "50259": {
61
- "content": "<eos>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "50260": {
69
- "content": "<pad>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "50261": {
77
- "content": "<unk>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "50262": {
85
- "content": "<sep>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "50263": {
93
- "content": "<cls>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "50264": {
101
- "content": "<mask>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "50265": {
109
- "content": "<greeting>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "50266": {
117
- "content": "<farewell>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "50267": {
125
- "content": "<thank>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "50268": {
133
- "content": "<apology>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "50269": {
141
- "content": "[PAD]",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "50270": {
149
- "content": "intelligent",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50271": {
157
- "content": "amazeballs",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50272": {
165
- "content": "cryptocurrency",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50273": {
173
- "content": "webinar",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50274": {
181
- "content": "vlog",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50275": {
189
- "content": "upcycle",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50276": {
197
- "content": "photobomb",
198
- "lstrip": false,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "50277": {
205
- "content": "facepalm",
206
- "lstrip": false,
207
- "normalized": true,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "50278": {
213
- "content": "crowdfunding",
214
- "lstrip": false,
215
- "normalized": true,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "50279": {
221
- "content": "bromance",
222
- "lstrip": false,
223
- "normalized": true,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "50280": {
229
- "content": "hangry",
230
- "lstrip": false,
231
- "normalized": true,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "50281": {
237
- "content": "empathy",
238
- "lstrip": false,
239
- "normalized": true,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "50282": {
245
- "content": "active_listening",
246
- "lstrip": false,
247
- "normalized": true,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "50283": {
253
- "content": "open_ended_question",
254
- "lstrip": false,
255
- "normalized": true,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "50284": {
261
- "content": "reflective_summary",
262
- "lstrip": false,
263
- "normalized": true,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "50285": {
269
- "content": "active_listener",
270
- "lstrip": false,
271
- "normalized": true,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "50286": {
277
- "content": "emotional_intelligence",
278
- "lstrip": false,
279
- "normalized": true,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "50287": {
285
- "content": "interpersonal_skill",
286
- "lstrip": false,
287
- "normalized": true,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "50288": {
293
- "content": "non_verbal_cue",
294
- "lstrip": false,
295
- "normalized": true,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "50289": {
301
- "content": "personal_boundaries",
302
- "lstrip": false,
303
- "normalized": true,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "50290": {
309
- "content": "active_listener",
310
- "lstrip": false,
311
- "normalized": true,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "50291": {
317
- "content": "non_judgmental",
318
- "lstrip": false,
319
- "normalized": true,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "50292": {
325
- "content": "cultural_sensitivity",
326
- "lstrip": false,
327
- "normalized": true,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "50293": {
333
- "content": "emotional_regulation",
334
- "lstrip": false,
335
- "normalized": true,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "50294": {
341
- "content": "self_awareness",
342
- "lstrip": false,
343
- "normalized": true,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "50295": {
349
- "content": "social_skill",
350
- "lstrip": false,
351
- "normalized": true,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "50296": {
357
- "content": "communication_style",
358
- "lstrip": false,
359
- "normalized": true,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "50297": {
365
- "content": "conversational_skill",
366
- "lstrip": false,
367
- "normalized": true,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "50298": {
373
- "content": "emotional_literacy",
374
- "lstrip": false,
375
- "normalized": true,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "50299": {
381
- "content": "interpersonal_communication",
382
- "lstrip": false,
383
- "normalized": true,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "50300": {
389
- "content": "resilience",
390
- "lstrip": false,
391
- "normalized": true,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "50301": {
397
- "content": "stress_management",
398
- "lstrip": false,
399
- "normalized": true,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "50302": {
405
- "content": "self_management",
406
- "lstrip": false,
407
- "normalized": true,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "50303": {
413
- "content": "self_efficacy",
414
- "lstrip": false,
415
- "normalized": true,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "50304": {
421
- "content": "self_motivation",
422
- "lstrip": false,
423
- "normalized": true,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "50305": {
429
- "content": "self_control",
430
- "lstrip": false,
431
- "normalized": true,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "50306": {
437
- "content": "self_esteem",
438
- "lstrip": false,
439
- "normalized": true,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "50307": {
445
- "content": "emotional_balance",
446
- "lstrip": false,
447
- "normalized": true,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "50308": {
453
- "content": "stress_reduction",
454
- "lstrip": false,
455
- "normalized": true,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "50309": {
461
- "content": "goal_setting",
462
- "lstrip": false,
463
- "normalized": true,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "50310": {
469
- "content": "time_management",
470
- "lstrip": false,
471
- "normalized": true,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "50311": {
477
- "content": "organization_skill",
478
- "lstrip": false,
479
- "normalized": true,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "50312": {
485
- "content": "self_directed_learning",
486
- "lstrip": false,
487
- "normalized": true,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "50313": {
493
- "content": "self_reflection",
494
- "lstrip": false,
495
- "normalized": true,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "50314": {
501
- "content": "empathy_map",
502
- "lstrip": false,
503
- "normalized": true,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "50315": {
509
- "content": "interpersonal_relationship",
510
- "lstrip": false,
511
- "normalized": true,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "50316": {
517
- "content": "personal_growth",
518
- "lstrip": false,
519
- "normalized": true,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "50317": {
525
- "content": "personal_development",
526
- "lstrip": false,
527
- "normalized": true,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "50318": {
533
- "content": "mindfulness",
534
- "lstrip": false,
535
- "normalized": true,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "50319": {
541
- "content": "personal_well_being",
542
- "lstrip": false,
543
- "normalized": true,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "50320": {
549
- "content": "personal_resilience",
550
- "lstrip": false,
551
- "normalized": true,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "50321": {
557
- "content": "self_care",
558
- "lstrip": false,
559
- "normalized": true,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "50322": {
565
- "content": "self_improvement",
566
- "lstrip": false,
567
- "normalized": true,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "50323": {
573
- "content": "personal_growth_plan",
574
- "lstrip": false,
575
- "normalized": true,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "50324": {
581
- "content": "life_skill",
582
- "lstrip": false,
583
- "normalized": true,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "50325": {
589
- "content": "self_renewal",
590
- "lstrip": false,
591
- "normalized": true,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "50326": {
597
- "content": "self_growth",
598
- "lstrip": false,
599
- "normalized": true,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- }
604
- },
605
- "additional_special_tokens": [
606
- "<greeting>",
607
- "<farewell>",
608
- "<thank>",
609
- "<apology>"
610
- ],
611
- "additional_vocab_files": {
612
- "bpe_merges_file": "merges.txt",
613
- "bpe_vocab_file": "vocab.json"
614
- },
615
- "advanced_options": {
616
- "dynamic_padding": true,
617
- "language_model_integration": {
618
- "enable": true,
619
- "models": [
620
- "bert-base-uncased",
621
- "roberta-base"
622
- ]
623
- },
624
- "lexical_analysis": {
625
- "enable": true,
626
- "methods": [
627
- "morphological",
628
- "syntactic",
629
- "semantic"
630
- ]
631
- },
632
- "subword_regularization": {
633
- "enable": true,
634
- "techniques": [
635
- "sampling",
636
- "dropping"
637
- ]
638
- }
639
- },
640
- "bos_token": "<bos>",
641
- "bpe_dropout": 0.1,
642
- "clean_up_tokenization_spaces": true,
643
- "cls_token": "<cls>",
644
- "do_lower_case": false,
645
- "enable_sentencepiece": true,
646
- "eos_token": "<eos>",
647
- "interleaved_tokenization": true,
648
- "mask_token": "<mask>",
649
- "max_length": 1024,
650
- "model_max_length": 1024,
651
- "pad_to_multiple_of": null,
652
- "pad_token": "<pad>",
653
- "pad_token_type_id": 0,
654
- "padding_side": "right",
655
- "sentence_piece_model_path": "spiece.model",
656
- "sep_token": "<sep>",
657
- "special_tokens_map_file": "special_tokens_map.json",
658
- "stride": 0,
659
- "strip_accents": null,
660
- "tokenizer_class": "GPT2Tokenizer",
661
- "truncation_side": "right",
662
- "truncation_strategy": "longest_first",
663
- "unk_token": "<unk>",
664
- "use_auth_token": true,
665
- "use_fast_tokenizer": true,
666
- "wordpieces_prefix": "##"
667
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[BOS]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[EOS]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "[BOS]",
61
+ "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "eos_token": "[EOS]",
64
+ "mask_token": "[MASK]",
65
+ "max_length": 1024,
66
+ "model_max_length": 1024,
67
+ "pad_token": "[UNK]",
68
+ "padding": "max_length",
69
+ "sep_token": "[SEP]",
70
+ "tokenizer_class": "PreTrainedTokenizerFast",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "[UNK]"
73
+ }