CryptoYogi commited on
Commit
1810d25
Β·
verified Β·
1 Parent(s): 6bf51ec

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +9 -21
  2. generation_config.json +3 -5
  3. model.safetensors +2 -2
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +255 -1982
config.json CHANGED
@@ -5,11 +5,10 @@
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 204,
8
- "dtype": "float32",
9
  "eos_token_id": 213,
10
  "head_dim": 256,
11
  "hidden_act": "gelu",
12
- "hidden_activation": null,
13
  "hidden_size": 2048,
14
  "initializer_range": 0.02,
15
  "intermediate_size": 16384,
@@ -19,25 +18,14 @@
19
  "num_hidden_layers": 18,
20
  "num_key_value_heads": 1,
21
  "pad_token_id": 0,
22
- "quantization_config": {
23
- "_load_in_4bit": true,
24
- "_load_in_8bit": false,
25
- "bnb_4bit_compute_dtype": "bfloat16",
26
- "bnb_4bit_quant_storage": "uint8",
27
- "bnb_4bit_quant_type": "nf4",
28
- "bnb_4bit_use_double_quant": true,
29
- "llm_int8_enable_fp32_cpu_offload": false,
30
- "llm_int8_has_fp16_weight": false,
31
- "llm_int8_skip_modules": null,
32
- "llm_int8_threshold": 6.0,
33
- "load_in_4bit": true,
34
- "load_in_8bit": false,
35
- "quant_method": "bitsandbytes"
36
- },
37
  "rms_norm_eps": 1e-06,
38
- "rope_scaling": null,
39
- "rope_theta": 10000.0,
40
- "transformers_version": "4.57.1",
41
- "use_cache": true,
 
 
 
 
42
  "vocab_size": 256000
43
  }
 
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 204,
8
+ "dtype": "float16",
9
  "eos_token_id": 213,
10
  "head_dim": 256,
11
  "hidden_act": "gelu",
 
12
  "hidden_size": 2048,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 16384,
 
18
  "num_hidden_layers": 18,
19
  "num_key_value_heads": 1,
20
  "pad_token_id": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "rms_norm_eps": 1e-06,
22
+ "rope_parameters": {
23
+ "rope_theta": 10000.0,
24
+ "rope_type": "default"
25
+ },
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "5.0.0",
28
+ "use_bidirectional_attention": null,
29
+ "use_cache": false,
30
  "vocab_size": 256000
31
  }
generation_config.json CHANGED
@@ -1,10 +1,8 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 204,
4
  "do_sample": true,
5
- "eos_token_id": [
6
- 213
7
- ],
8
  "pad_token_id": 0,
9
- "transformers_version": "4.57.1"
10
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 2,
4
  "do_sample": true,
5
+ "eos_token_id": 1,
 
 
6
  "pad_token_id": 0,
7
+ "transformers_version": "5.0.0"
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a04c3a9a0adc486453c3eff8bd46409cc819d817b3e30cf06b95457e00f4998b
3
- size 3120064752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe5cb4a2c18dd909193a40117ccac96baaaca569f2a3cbdde034cbd75d07e64
3
+ size 5012363688
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a94b40b179062232e0ba07cc23bd322362310c3cbf4d015bc1e989e86714b827
3
- size 34362407
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4cdd71a6ece19c50b2b69fb6ee68b934c151d65aa0ba5ea025987f9cb15bbb
3
+ size 34358406
tokenizer_config.json CHANGED
@@ -1,1989 +1,261 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<pad>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "3": {
14
- "content": "<unk>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "4": {
22
- "content": "<mask>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "5": {
30
- "content": "<2mass>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "6": {
38
- "content": "[@BOS@]",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "7": {
46
- "content": "<unused0>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "8": {
54
- "content": "<unused1>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "9": {
62
- "content": "<unused2>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "10": {
70
- "content": "<unused3>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": false
76
- },
77
- "11": {
78
- "content": "<unused4>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": false
84
- },
85
- "12": {
86
- "content": "<unused5>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": false
92
- },
93
- "13": {
94
- "content": "<unused6>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": false
100
- },
101
- "14": {
102
- "content": "<unused7>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": false
108
- },
109
- "15": {
110
- "content": "<unused8>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": false
116
- },
117
- "16": {
118
- "content": "<unused9>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "17": {
126
- "content": "<unused10>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "18": {
134
- "content": "<unused11>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "19": {
142
- "content": "<unused12>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "20": {
150
- "content": "<unused13>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "21": {
158
- "content": "<unused14>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "22": {
166
- "content": "<unused15>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "23": {
174
- "content": "<unused16>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "24": {
182
- "content": "<unused17>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "25": {
190
- "content": "<unused18>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "26": {
198
- "content": "<unused19>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "27": {
206
- "content": "<unused20>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- },
213
- "28": {
214
- "content": "<unused21>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": false
220
- },
221
- "29": {
222
- "content": "<unused22>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": false
228
- },
229
- "30": {
230
- "content": "<unused23>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": false
236
- },
237
- "31": {
238
- "content": "<unused24>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": false
244
- },
245
- "32": {
246
- "content": "<unused25>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": false
252
- },
253
- "33": {
254
- "content": "<unused26>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": false
260
- },
261
- "34": {
262
- "content": "<unused27>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": false
268
- },
269
- "35": {
270
- "content": "<unused28>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": false
276
- },
277
- "36": {
278
- "content": "<unused29>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": false
284
- },
285
- "37": {
286
- "content": "<unused30>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": false
292
- },
293
- "38": {
294
- "content": "<unused31>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": false,
298
- "single_word": false,
299
- "special": false
300
- },
301
- "39": {
302
- "content": "<unused32>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": false,
306
- "single_word": false,
307
- "special": false
308
- },
309
- "40": {
310
- "content": "<unused33>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": false,
314
- "single_word": false,
315
- "special": false
316
- },
317
- "41": {
318
- "content": "<unused34>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": false,
322
- "single_word": false,
323
- "special": false
324
- },
325
- "42": {
326
- "content": "<unused35>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": false,
330
- "single_word": false,
331
- "special": false
332
- },
333
- "43": {
334
- "content": "<unused36>",
335
- "lstrip": false,
336
- "normalized": false,
337
- "rstrip": false,
338
- "single_word": false,
339
- "special": false
340
- },
341
- "44": {
342
- "content": "<unused37>",
343
- "lstrip": false,
344
- "normalized": false,
345
- "rstrip": false,
346
- "single_word": false,
347
- "special": false
348
- },
349
- "45": {
350
- "content": "<unused38>",
351
- "lstrip": false,
352
- "normalized": false,
353
- "rstrip": false,
354
- "single_word": false,
355
- "special": false
356
- },
357
- "46": {
358
- "content": "<unused39>",
359
- "lstrip": false,
360
- "normalized": false,
361
- "rstrip": false,
362
- "single_word": false,
363
- "special": false
364
- },
365
- "47": {
366
- "content": "<unused40>",
367
- "lstrip": false,
368
- "normalized": false,
369
- "rstrip": false,
370
- "single_word": false,
371
- "special": false
372
- },
373
- "48": {
374
- "content": "<unused41>",
375
- "lstrip": false,
376
- "normalized": false,
377
- "rstrip": false,
378
- "single_word": false,
379
- "special": false
380
- },
381
- "49": {
382
- "content": "<unused42>",
383
- "lstrip": false,
384
- "normalized": false,
385
- "rstrip": false,
386
- "single_word": false,
387
- "special": false
388
- },
389
- "50": {
390
- "content": "<unused43>",
391
- "lstrip": false,
392
- "normalized": false,
393
- "rstrip": false,
394
- "single_word": false,
395
- "special": false
396
- },
397
- "51": {
398
- "content": "<unused44>",
399
- "lstrip": false,
400
- "normalized": false,
401
- "rstrip": false,
402
- "single_word": false,
403
- "special": false
404
- },
405
- "52": {
406
- "content": "<unused45>",
407
- "lstrip": false,
408
- "normalized": false,
409
- "rstrip": false,
410
- "single_word": false,
411
- "special": false
412
- },
413
- "53": {
414
- "content": "<unused46>",
415
- "lstrip": false,
416
- "normalized": false,
417
- "rstrip": false,
418
- "single_word": false,
419
- "special": false
420
- },
421
- "54": {
422
- "content": "<unused47>",
423
- "lstrip": false,
424
- "normalized": false,
425
- "rstrip": false,
426
- "single_word": false,
427
- "special": false
428
- },
429
- "55": {
430
- "content": "<unused48>",
431
- "lstrip": false,
432
- "normalized": false,
433
- "rstrip": false,
434
- "single_word": false,
435
- "special": false
436
- },
437
- "56": {
438
- "content": "<unused49>",
439
- "lstrip": false,
440
- "normalized": false,
441
- "rstrip": false,
442
- "single_word": false,
443
- "special": false
444
- },
445
- "57": {
446
- "content": "<unused50>",
447
- "lstrip": false,
448
- "normalized": false,
449
- "rstrip": false,
450
- "single_word": false,
451
- "special": false
452
- },
453
- "58": {
454
- "content": "<unused51>",
455
- "lstrip": false,
456
- "normalized": false,
457
- "rstrip": false,
458
- "single_word": false,
459
- "special": false
460
- },
461
- "59": {
462
- "content": "<unused52>",
463
- "lstrip": false,
464
- "normalized": false,
465
- "rstrip": false,
466
- "single_word": false,
467
- "special": false
468
- },
469
- "60": {
470
- "content": "<unused53>",
471
- "lstrip": false,
472
- "normalized": false,
473
- "rstrip": false,
474
- "single_word": false,
475
- "special": false
476
- },
477
- "61": {
478
- "content": "<unused54>",
479
- "lstrip": false,
480
- "normalized": false,
481
- "rstrip": false,
482
- "single_word": false,
483
- "special": false
484
- },
485
- "62": {
486
- "content": "<unused55>",
487
- "lstrip": false,
488
- "normalized": false,
489
- "rstrip": false,
490
- "single_word": false,
491
- "special": false
492
- },
493
- "63": {
494
- "content": "<unused56>",
495
- "lstrip": false,
496
- "normalized": false,
497
- "rstrip": false,
498
- "single_word": false,
499
- "special": false
500
- },
501
- "64": {
502
- "content": "<unused57>",
503
- "lstrip": false,
504
- "normalized": false,
505
- "rstrip": false,
506
- "single_word": false,
507
- "special": false
508
- },
509
- "65": {
510
- "content": "<unused58>",
511
- "lstrip": false,
512
- "normalized": false,
513
- "rstrip": false,
514
- "single_word": false,
515
- "special": false
516
- },
517
- "66": {
518
- "content": "<unused59>",
519
- "lstrip": false,
520
- "normalized": false,
521
- "rstrip": false,
522
- "single_word": false,
523
- "special": false
524
- },
525
- "67": {
526
- "content": "<unused60>",
527
- "lstrip": false,
528
- "normalized": false,
529
- "rstrip": false,
530
- "single_word": false,
531
- "special": false
532
- },
533
- "68": {
534
- "content": "<unused61>",
535
- "lstrip": false,
536
- "normalized": false,
537
- "rstrip": false,
538
- "single_word": false,
539
- "special": false
540
- },
541
- "69": {
542
- "content": "<unused62>",
543
- "lstrip": false,
544
- "normalized": false,
545
- "rstrip": false,
546
- "single_word": false,
547
- "special": false
548
- },
549
- "70": {
550
- "content": "<unused63>",
551
- "lstrip": false,
552
- "normalized": false,
553
- "rstrip": false,
554
- "single_word": false,
555
- "special": false
556
- },
557
- "71": {
558
- "content": "<unused64>",
559
- "lstrip": false,
560
- "normalized": false,
561
- "rstrip": false,
562
- "single_word": false,
563
- "special": false
564
- },
565
- "72": {
566
- "content": "<unused65>",
567
- "lstrip": false,
568
- "normalized": false,
569
- "rstrip": false,
570
- "single_word": false,
571
- "special": false
572
- },
573
- "73": {
574
- "content": "<unused66>",
575
- "lstrip": false,
576
- "normalized": false,
577
- "rstrip": false,
578
- "single_word": false,
579
- "special": false
580
- },
581
- "74": {
582
- "content": "<unused67>",
583
- "lstrip": false,
584
- "normalized": false,
585
- "rstrip": false,
586
- "single_word": false,
587
- "special": false
588
- },
589
- "75": {
590
- "content": "<unused68>",
591
- "lstrip": false,
592
- "normalized": false,
593
- "rstrip": false,
594
- "single_word": false,
595
- "special": false
596
- },
597
- "76": {
598
- "content": "<unused69>",
599
- "lstrip": false,
600
- "normalized": false,
601
- "rstrip": false,
602
- "single_word": false,
603
- "special": false
604
- },
605
- "77": {
606
- "content": "<unused70>",
607
- "lstrip": false,
608
- "normalized": false,
609
- "rstrip": false,
610
- "single_word": false,
611
- "special": false
612
- },
613
- "78": {
614
- "content": "<unused71>",
615
- "lstrip": false,
616
- "normalized": false,
617
- "rstrip": false,
618
- "single_word": false,
619
- "special": false
620
- },
621
- "79": {
622
- "content": "<unused72>",
623
- "lstrip": false,
624
- "normalized": false,
625
- "rstrip": false,
626
- "single_word": false,
627
- "special": false
628
- },
629
- "80": {
630
- "content": "<unused73>",
631
- "lstrip": false,
632
- "normalized": false,
633
- "rstrip": false,
634
- "single_word": false,
635
- "special": false
636
- },
637
- "81": {
638
- "content": "<unused74>",
639
- "lstrip": false,
640
- "normalized": false,
641
- "rstrip": false,
642
- "single_word": false,
643
- "special": false
644
- },
645
- "82": {
646
- "content": "<unused75>",
647
- "lstrip": false,
648
- "normalized": false,
649
- "rstrip": false,
650
- "single_word": false,
651
- "special": false
652
- },
653
- "83": {
654
- "content": "<unused76>",
655
- "lstrip": false,
656
- "normalized": false,
657
- "rstrip": false,
658
- "single_word": false,
659
- "special": false
660
- },
661
- "84": {
662
- "content": "<unused77>",
663
- "lstrip": false,
664
- "normalized": false,
665
- "rstrip": false,
666
- "single_word": false,
667
- "special": false
668
- },
669
- "85": {
670
- "content": "<unused78>",
671
- "lstrip": false,
672
- "normalized": false,
673
- "rstrip": false,
674
- "single_word": false,
675
- "special": false
676
- },
677
- "86": {
678
- "content": "<unused79>",
679
- "lstrip": false,
680
- "normalized": false,
681
- "rstrip": false,
682
- "single_word": false,
683
- "special": false
684
- },
685
- "87": {
686
- "content": "<unused80>",
687
- "lstrip": false,
688
- "normalized": false,
689
- "rstrip": false,
690
- "single_word": false,
691
- "special": false
692
- },
693
- "88": {
694
- "content": "<unused81>",
695
- "lstrip": false,
696
- "normalized": false,
697
- "rstrip": false,
698
- "single_word": false,
699
- "special": false
700
- },
701
- "89": {
702
- "content": "<unused82>",
703
- "lstrip": false,
704
- "normalized": false,
705
- "rstrip": false,
706
- "single_word": false,
707
- "special": false
708
- },
709
- "90": {
710
- "content": "<unused83>",
711
- "lstrip": false,
712
- "normalized": false,
713
- "rstrip": false,
714
- "single_word": false,
715
- "special": false
716
- },
717
- "91": {
718
- "content": "<unused84>",
719
- "lstrip": false,
720
- "normalized": false,
721
- "rstrip": false,
722
- "single_word": false,
723
- "special": false
724
- },
725
- "92": {
726
- "content": "<unused85>",
727
- "lstrip": false,
728
- "normalized": false,
729
- "rstrip": false,
730
- "single_word": false,
731
- "special": false
732
- },
733
- "93": {
734
- "content": "<unused86>",
735
- "lstrip": false,
736
- "normalized": false,
737
- "rstrip": false,
738
- "single_word": false,
739
- "special": false
740
- },
741
- "94": {
742
- "content": "<unused87>",
743
- "lstrip": false,
744
- "normalized": false,
745
- "rstrip": false,
746
- "single_word": false,
747
- "special": false
748
- },
749
- "95": {
750
- "content": "<unused88>",
751
- "lstrip": false,
752
- "normalized": false,
753
- "rstrip": false,
754
- "single_word": false,
755
- "special": false
756
- },
757
- "96": {
758
- "content": "<unused89>",
759
- "lstrip": false,
760
- "normalized": false,
761
- "rstrip": false,
762
- "single_word": false,
763
- "special": false
764
- },
765
- "97": {
766
- "content": "<unused90>",
767
- "lstrip": false,
768
- "normalized": false,
769
- "rstrip": false,
770
- "single_word": false,
771
- "special": false
772
- },
773
- "98": {
774
- "content": "<unused91>",
775
- "lstrip": false,
776
- "normalized": false,
777
- "rstrip": false,
778
- "single_word": false,
779
- "special": false
780
- },
781
- "99": {
782
- "content": "<unused92>",
783
- "lstrip": false,
784
- "normalized": false,
785
- "rstrip": false,
786
- "single_word": false,
787
- "special": false
788
- },
789
- "100": {
790
- "content": "<unused93>",
791
- "lstrip": false,
792
- "normalized": false,
793
- "rstrip": false,
794
- "single_word": false,
795
- "special": false
796
- },
797
- "101": {
798
- "content": "<unused94>",
799
- "lstrip": false,
800
- "normalized": false,
801
- "rstrip": false,
802
- "single_word": false,
803
- "special": false
804
- },
805
- "102": {
806
- "content": "<unused95>",
807
- "lstrip": false,
808
- "normalized": false,
809
- "rstrip": false,
810
- "single_word": false,
811
- "special": false
812
- },
813
- "103": {
814
- "content": "<unused96>",
815
- "lstrip": false,
816
- "normalized": false,
817
- "rstrip": false,
818
- "single_word": false,
819
- "special": false
820
- },
821
- "104": {
822
- "content": "<unused97>",
823
- "lstrip": false,
824
- "normalized": false,
825
- "rstrip": false,
826
- "single_word": false,
827
- "special": false
828
- },
829
- "105": {
830
- "content": "<unused98>",
831
- "lstrip": false,
832
- "normalized": false,
833
- "rstrip": false,
834
- "single_word": false,
835
- "special": false
836
- },
837
- "106": {
838
- "content": "<start_of_turn>",
839
- "lstrip": false,
840
- "normalized": false,
841
- "rstrip": false,
842
- "single_word": false,
843
- "special": true
844
- },
845
- "107": {
846
- "content": "<end_of_turn>",
847
- "lstrip": false,
848
- "normalized": false,
849
- "rstrip": false,
850
- "single_word": false,
851
- "special": true
852
- },
853
- "108": {
854
- "content": "\n",
855
- "lstrip": false,
856
- "normalized": false,
857
- "rstrip": false,
858
- "single_word": false,
859
- "special": false
860
- },
861
- "109": {
862
- "content": "\n\n",
863
- "lstrip": false,
864
- "normalized": false,
865
- "rstrip": false,
866
- "single_word": false,
867
- "special": false
868
- },
869
- "110": {
870
- "content": "\n\n\n",
871
- "lstrip": false,
872
- "normalized": false,
873
- "rstrip": false,
874
- "single_word": false,
875
- "special": false
876
- },
877
- "111": {
878
- "content": "\n\n\n\n",
879
- "lstrip": false,
880
- "normalized": false,
881
- "rstrip": false,
882
- "single_word": false,
883
- "special": false
884
- },
885
- "112": {
886
- "content": "\n\n\n\n\n",
887
- "lstrip": false,
888
- "normalized": false,
889
- "rstrip": false,
890
- "single_word": false,
891
- "special": false
892
- },
893
- "113": {
894
- "content": "\n\n\n\n\n\n",
895
- "lstrip": false,
896
- "normalized": false,
897
- "rstrip": false,
898
- "single_word": false,
899
- "special": false
900
- },
901
- "114": {
902
- "content": "\n\n\n\n\n\n\n",
903
- "lstrip": false,
904
- "normalized": false,
905
- "rstrip": false,
906
- "single_word": false,
907
- "special": false
908
- },
909
- "115": {
910
- "content": "\n\n\n\n\n\n\n\n",
911
- "lstrip": false,
912
- "normalized": false,
913
- "rstrip": false,
914
- "single_word": false,
915
- "special": false
916
- },
917
- "116": {
918
- "content": "\n\n\n\n\n\n\n\n\n",
919
- "lstrip": false,
920
- "normalized": false,
921
- "rstrip": false,
922
- "single_word": false,
923
- "special": false
924
- },
925
- "117": {
926
- "content": "\n\n\n\n\n\n\n\n\n\n",
927
- "lstrip": false,
928
- "normalized": false,
929
- "rstrip": false,
930
- "single_word": false,
931
- "special": false
932
- },
933
- "118": {
934
- "content": "\n\n\n\n\n\n\n\n\n\n\n",
935
- "lstrip": false,
936
- "normalized": false,
937
- "rstrip": false,
938
- "single_word": false,
939
- "special": false
940
- },
941
- "119": {
942
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
943
- "lstrip": false,
944
- "normalized": false,
945
- "rstrip": false,
946
- "single_word": false,
947
- "special": false
948
- },
949
- "120": {
950
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
951
- "lstrip": false,
952
- "normalized": false,
953
- "rstrip": false,
954
- "single_word": false,
955
- "special": false
956
- },
957
- "121": {
958
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
959
- "lstrip": false,
960
- "normalized": false,
961
- "rstrip": false,
962
- "single_word": false,
963
- "special": false
964
- },
965
- "122": {
966
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
- "lstrip": false,
968
- "normalized": false,
969
- "rstrip": false,
970
- "single_word": false,
971
- "special": false
972
- },
973
- "123": {
974
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
- "lstrip": false,
976
- "normalized": false,
977
- "rstrip": false,
978
- "single_word": false,
979
- "special": false
980
- },
981
- "124": {
982
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
- "lstrip": false,
984
- "normalized": false,
985
- "rstrip": false,
986
- "single_word": false,
987
- "special": false
988
- },
989
- "125": {
990
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
- "lstrip": false,
992
- "normalized": false,
993
- "rstrip": false,
994
- "single_word": false,
995
- "special": false
996
- },
997
- "126": {
998
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
- "lstrip": false,
1000
- "normalized": false,
1001
- "rstrip": false,
1002
- "single_word": false,
1003
- "special": false
1004
- },
1005
- "127": {
1006
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
- "lstrip": false,
1008
- "normalized": false,
1009
- "rstrip": false,
1010
- "single_word": false,
1011
- "special": false
1012
- },
1013
- "128": {
1014
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
- "lstrip": false,
1016
- "normalized": false,
1017
- "rstrip": false,
1018
- "single_word": false,
1019
- "special": false
1020
- },
1021
- "129": {
1022
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
- "lstrip": false,
1024
- "normalized": false,
1025
- "rstrip": false,
1026
- "single_word": false,
1027
- "special": false
1028
- },
1029
- "130": {
1030
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
- "lstrip": false,
1032
- "normalized": false,
1033
- "rstrip": false,
1034
- "single_word": false,
1035
- "special": false
1036
- },
1037
- "131": {
1038
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
- "lstrip": false,
1040
- "normalized": false,
1041
- "rstrip": false,
1042
- "single_word": false,
1043
- "special": false
1044
- },
1045
- "132": {
1046
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
- "lstrip": false,
1048
- "normalized": false,
1049
- "rstrip": false,
1050
- "single_word": false,
1051
- "special": false
1052
- },
1053
- "133": {
1054
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
- "lstrip": false,
1056
- "normalized": false,
1057
- "rstrip": false,
1058
- "single_word": false,
1059
- "special": false
1060
- },
1061
- "134": {
1062
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
- "lstrip": false,
1064
- "normalized": false,
1065
- "rstrip": false,
1066
- "single_word": false,
1067
- "special": false
1068
- },
1069
- "135": {
1070
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
- "lstrip": false,
1072
- "normalized": false,
1073
- "rstrip": false,
1074
- "single_word": false,
1075
- "special": false
1076
- },
1077
- "136": {
1078
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
- "lstrip": false,
1080
- "normalized": false,
1081
- "rstrip": false,
1082
- "single_word": false,
1083
- "special": false
1084
- },
1085
- "137": {
1086
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
- "lstrip": false,
1088
- "normalized": false,
1089
- "rstrip": false,
1090
- "single_word": false,
1091
- "special": false
1092
- },
1093
- "138": {
1094
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
- "lstrip": false,
1096
- "normalized": false,
1097
- "rstrip": false,
1098
- "single_word": false,
1099
- "special": false
1100
- },
1101
- "139": {
1102
- "content": "▁▁",
1103
- "lstrip": false,
1104
- "normalized": false,
1105
- "rstrip": false,
1106
- "single_word": false,
1107
- "special": false
1108
- },
1109
- "140": {
1110
- "content": "▁▁▁",
1111
- "lstrip": false,
1112
- "normalized": false,
1113
- "rstrip": false,
1114
- "single_word": false,
1115
- "special": false
1116
- },
1117
- "141": {
1118
- "content": "▁▁▁▁",
1119
- "lstrip": false,
1120
- "normalized": false,
1121
- "rstrip": false,
1122
- "single_word": false,
1123
- "special": false
1124
- },
1125
- "142": {
1126
- "content": "▁▁▁▁▁",
1127
- "lstrip": false,
1128
- "normalized": false,
1129
- "rstrip": false,
1130
- "single_word": false,
1131
- "special": false
1132
- },
1133
- "143": {
1134
- "content": "▁▁▁▁▁▁",
1135
- "lstrip": false,
1136
- "normalized": false,
1137
- "rstrip": false,
1138
- "single_word": false,
1139
- "special": false
1140
- },
1141
- "144": {
1142
- "content": "▁▁▁▁▁▁▁",
1143
- "lstrip": false,
1144
- "normalized": false,
1145
- "rstrip": false,
1146
- "single_word": false,
1147
- "special": false
1148
- },
1149
- "145": {
1150
- "content": "▁▁▁▁▁▁▁▁",
1151
- "lstrip": false,
1152
- "normalized": false,
1153
- "rstrip": false,
1154
- "single_word": false,
1155
- "special": false
1156
- },
1157
- "146": {
1158
- "content": "▁▁▁▁▁▁▁▁▁",
1159
- "lstrip": false,
1160
- "normalized": false,
1161
- "rstrip": false,
1162
- "single_word": false,
1163
- "special": false
1164
- },
1165
- "147": {
1166
- "content": "▁▁▁▁▁▁▁▁▁▁",
1167
- "lstrip": false,
1168
- "normalized": false,
1169
- "rstrip": false,
1170
- "single_word": false,
1171
- "special": false
1172
- },
1173
- "148": {
1174
- "content": "▁▁▁▁▁▁▁▁▁▁▁",
1175
- "lstrip": false,
1176
- "normalized": false,
1177
- "rstrip": false,
1178
- "single_word": false,
1179
- "special": false
1180
- },
1181
- "149": {
1182
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1183
- "lstrip": false,
1184
- "normalized": false,
1185
- "rstrip": false,
1186
- "single_word": false,
1187
- "special": false
1188
- },
1189
- "150": {
1190
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1191
- "lstrip": false,
1192
- "normalized": false,
1193
- "rstrip": false,
1194
- "single_word": false,
1195
- "special": false
1196
- },
1197
- "151": {
1198
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1199
- "lstrip": false,
1200
- "normalized": false,
1201
- "rstrip": false,
1202
- "single_word": false,
1203
- "special": false
1204
- },
1205
- "152": {
1206
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
- "lstrip": false,
1208
- "normalized": false,
1209
- "rstrip": false,
1210
- "single_word": false,
1211
- "special": false
1212
- },
1213
- "153": {
1214
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
- "lstrip": false,
1216
- "normalized": false,
1217
- "rstrip": false,
1218
- "single_word": false,
1219
- "special": false
1220
- },
1221
- "154": {
1222
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
- "lstrip": false,
1224
- "normalized": false,
1225
- "rstrip": false,
1226
- "single_word": false,
1227
- "special": false
1228
- },
1229
- "155": {
1230
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
- "lstrip": false,
1232
- "normalized": false,
1233
- "rstrip": false,
1234
- "single_word": false,
1235
- "special": false
1236
- },
1237
- "156": {
1238
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
- "lstrip": false,
1240
- "normalized": false,
1241
- "rstrip": false,
1242
- "single_word": false,
1243
- "special": false
1244
- },
1245
- "157": {
1246
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
- "lstrip": false,
1248
- "normalized": false,
1249
- "rstrip": false,
1250
- "single_word": false,
1251
- "special": false
1252
- },
1253
- "158": {
1254
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
- "lstrip": false,
1256
- "normalized": false,
1257
- "rstrip": false,
1258
- "single_word": false,
1259
- "special": false
1260
- },
1261
- "159": {
1262
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
- "lstrip": false,
1264
- "normalized": false,
1265
- "rstrip": false,
1266
- "single_word": false,
1267
- "special": false
1268
- },
1269
- "160": {
1270
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
- "lstrip": false,
1272
- "normalized": false,
1273
- "rstrip": false,
1274
- "single_word": false,
1275
- "special": false
1276
- },
1277
- "161": {
1278
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
- "lstrip": false,
1280
- "normalized": false,
1281
- "rstrip": false,
1282
- "single_word": false,
1283
- "special": false
1284
- },
1285
- "162": {
1286
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
- "lstrip": false,
1288
- "normalized": false,
1289
- "rstrip": false,
1290
- "single_word": false,
1291
- "special": false
1292
- },
1293
- "163": {
1294
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
- "lstrip": false,
1296
- "normalized": false,
1297
- "rstrip": false,
1298
- "single_word": false,
1299
- "special": false
1300
- },
1301
- "164": {
1302
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
- "lstrip": false,
1304
- "normalized": false,
1305
- "rstrip": false,
1306
- "single_word": false,
1307
- "special": false
1308
- },
1309
- "165": {
1310
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
- "lstrip": false,
1312
- "normalized": false,
1313
- "rstrip": false,
1314
- "single_word": false,
1315
- "special": false
1316
- },
1317
- "166": {
1318
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
- "lstrip": false,
1320
- "normalized": false,
1321
- "rstrip": false,
1322
- "single_word": false,
1323
- "special": false
1324
- },
1325
- "167": {
1326
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
- "lstrip": false,
1328
- "normalized": false,
1329
- "rstrip": false,
1330
- "single_word": false,
1331
- "special": false
1332
- },
1333
- "168": {
1334
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
- "lstrip": false,
1336
- "normalized": false,
1337
- "rstrip": false,
1338
- "single_word": false,
1339
- "special": false
1340
- },
1341
- "169": {
1342
- "content": "<table>",
1343
- "lstrip": false,
1344
- "normalized": false,
1345
- "rstrip": false,
1346
- "single_word": false,
1347
- "special": false
1348
- },
1349
- "170": {
1350
- "content": "<caption>",
1351
- "lstrip": false,
1352
- "normalized": false,
1353
- "rstrip": false,
1354
- "single_word": false,
1355
- "special": false
1356
- },
1357
- "171": {
1358
- "content": "<thead>",
1359
- "lstrip": false,
1360
- "normalized": false,
1361
- "rstrip": false,
1362
- "single_word": false,
1363
- "special": false
1364
- },
1365
- "172": {
1366
- "content": "<tbody>",
1367
- "lstrip": false,
1368
- "normalized": false,
1369
- "rstrip": false,
1370
- "single_word": false,
1371
- "special": false
1372
- },
1373
- "173": {
1374
- "content": "<tfoot>",
1375
- "lstrip": false,
1376
- "normalized": false,
1377
- "rstrip": false,
1378
- "single_word": false,
1379
- "special": false
1380
- },
1381
- "174": {
1382
- "content": "<tr>",
1383
- "lstrip": false,
1384
- "normalized": false,
1385
- "rstrip": false,
1386
- "single_word": false,
1387
- "special": false
1388
- },
1389
- "175": {
1390
- "content": "<th>",
1391
- "lstrip": false,
1392
- "normalized": false,
1393
- "rstrip": false,
1394
- "single_word": false,
1395
- "special": false
1396
- },
1397
- "176": {
1398
- "content": "<td>",
1399
- "lstrip": false,
1400
- "normalized": false,
1401
- "rstrip": false,
1402
- "single_word": false,
1403
- "special": false
1404
- },
1405
- "177": {
1406
- "content": "</table>",
1407
- "lstrip": false,
1408
- "normalized": false,
1409
- "rstrip": false,
1410
- "single_word": false,
1411
- "special": false
1412
- },
1413
- "178": {
1414
- "content": "</caption>",
1415
- "lstrip": false,
1416
- "normalized": false,
1417
- "rstrip": false,
1418
- "single_word": false,
1419
- "special": false
1420
- },
1421
- "179": {
1422
- "content": "</thead>",
1423
- "lstrip": false,
1424
- "normalized": false,
1425
- "rstrip": false,
1426
- "single_word": false,
1427
- "special": false
1428
- },
1429
- "180": {
1430
- "content": "</tbody>",
1431
- "lstrip": false,
1432
- "normalized": false,
1433
- "rstrip": false,
1434
- "single_word": false,
1435
- "special": false
1436
- },
1437
- "181": {
1438
- "content": "</tfoot>",
1439
- "lstrip": false,
1440
- "normalized": false,
1441
- "rstrip": false,
1442
- "single_word": false,
1443
- "special": false
1444
- },
1445
- "182": {
1446
- "content": "</tr>",
1447
- "lstrip": false,
1448
- "normalized": false,
1449
- "rstrip": false,
1450
- "single_word": false,
1451
- "special": false
1452
- },
1453
- "183": {
1454
- "content": "</th>",
1455
- "lstrip": false,
1456
- "normalized": false,
1457
- "rstrip": false,
1458
- "single_word": false,
1459
- "special": false
1460
- },
1461
- "184": {
1462
- "content": "</td>",
1463
- "lstrip": false,
1464
- "normalized": false,
1465
- "rstrip": false,
1466
- "single_word": false,
1467
- "special": false
1468
- },
1469
- "185": {
1470
- "content": "<h1>",
1471
- "lstrip": false,
1472
- "normalized": false,
1473
- "rstrip": false,
1474
- "single_word": false,
1475
- "special": false
1476
- },
1477
- "186": {
1478
- "content": "<h2>",
1479
- "lstrip": false,
1480
- "normalized": false,
1481
- "rstrip": false,
1482
- "single_word": false,
1483
- "special": false
1484
- },
1485
- "187": {
1486
- "content": "<h3>",
1487
- "lstrip": false,
1488
- "normalized": false,
1489
- "rstrip": false,
1490
- "single_word": false,
1491
- "special": false
1492
- },
1493
- "188": {
1494
- "content": "<h4>",
1495
- "lstrip": false,
1496
- "normalized": false,
1497
- "rstrip": false,
1498
- "single_word": false,
1499
- "special": false
1500
- },
1501
- "189": {
1502
- "content": "<h5>",
1503
- "lstrip": false,
1504
- "normalized": false,
1505
- "rstrip": false,
1506
- "single_word": false,
1507
- "special": false
1508
- },
1509
- "190": {
1510
- "content": "<h6>",
1511
- "lstrip": false,
1512
- "normalized": false,
1513
- "rstrip": false,
1514
- "single_word": false,
1515
- "special": false
1516
- },
1517
- "191": {
1518
- "content": "<blockquote>",
1519
- "lstrip": false,
1520
- "normalized": false,
1521
- "rstrip": false,
1522
- "single_word": false,
1523
- "special": false
1524
- },
1525
- "192": {
1526
- "content": "</h1>",
1527
- "lstrip": false,
1528
- "normalized": false,
1529
- "rstrip": false,
1530
- "single_word": false,
1531
- "special": false
1532
- },
1533
- "193": {
1534
- "content": "</h2>",
1535
- "lstrip": false,
1536
- "normalized": false,
1537
- "rstrip": false,
1538
- "single_word": false,
1539
- "special": false
1540
- },
1541
- "194": {
1542
- "content": "</h3>",
1543
- "lstrip": false,
1544
- "normalized": false,
1545
- "rstrip": false,
1546
- "single_word": false,
1547
- "special": false
1548
- },
1549
- "195": {
1550
- "content": "</h4>",
1551
- "lstrip": false,
1552
- "normalized": false,
1553
- "rstrip": false,
1554
- "single_word": false,
1555
- "special": false
1556
- },
1557
- "196": {
1558
- "content": "</h5>",
1559
- "lstrip": false,
1560
- "normalized": false,
1561
- "rstrip": false,
1562
- "single_word": false,
1563
- "special": false
1564
- },
1565
- "197": {
1566
- "content": "</h6>",
1567
- "lstrip": false,
1568
- "normalized": false,
1569
- "rstrip": false,
1570
- "single_word": false,
1571
- "special": false
1572
- },
1573
- "198": {
1574
- "content": "</blockquote>",
1575
- "lstrip": false,
1576
- "normalized": false,
1577
- "rstrip": false,
1578
- "single_word": false,
1579
- "special": false
1580
- },
1581
- "199": {
1582
- "content": "<strong>",
1583
- "lstrip": false,
1584
- "normalized": false,
1585
- "rstrip": false,
1586
- "single_word": false,
1587
- "special": false
1588
- },
1589
- "200": {
1590
- "content": "<em>",
1591
- "lstrip": false,
1592
- "normalized": false,
1593
- "rstrip": false,
1594
- "single_word": false,
1595
- "special": false
1596
- },
1597
- "201": {
1598
- "content": "<b>",
1599
- "lstrip": false,
1600
- "normalized": false,
1601
- "rstrip": false,
1602
- "single_word": false,
1603
- "special": false
1604
- },
1605
- "202": {
1606
- "content": "<i>",
1607
- "lstrip": false,
1608
- "normalized": false,
1609
- "rstrip": false,
1610
- "single_word": false,
1611
- "special": false
1612
- },
1613
- "203": {
1614
- "content": "<u>",
1615
- "lstrip": false,
1616
- "normalized": false,
1617
- "rstrip": false,
1618
- "single_word": false,
1619
- "special": false
1620
- },
1621
- "204": {
1622
- "content": "<s>",
1623
- "lstrip": false,
1624
- "normalized": false,
1625
- "rstrip": false,
1626
- "single_word": false,
1627
- "special": true
1628
- },
1629
- "205": {
1630
- "content": "<sub>",
1631
- "lstrip": false,
1632
- "normalized": false,
1633
- "rstrip": false,
1634
- "single_word": false,
1635
- "special": false
1636
- },
1637
- "206": {
1638
- "content": "<sup>",
1639
- "lstrip": false,
1640
- "normalized": false,
1641
- "rstrip": false,
1642
- "single_word": false,
1643
- "special": false
1644
- },
1645
- "207": {
1646
- "content": "<code>",
1647
- "lstrip": false,
1648
- "normalized": false,
1649
- "rstrip": false,
1650
- "single_word": false,
1651
- "special": false
1652
- },
1653
- "208": {
1654
- "content": "</strong>",
1655
- "lstrip": false,
1656
- "normalized": false,
1657
- "rstrip": false,
1658
- "single_word": false,
1659
- "special": false
1660
- },
1661
- "209": {
1662
- "content": "</em>",
1663
- "lstrip": false,
1664
- "normalized": false,
1665
- "rstrip": false,
1666
- "single_word": false,
1667
- "special": false
1668
- },
1669
- "210": {
1670
- "content": "</b>",
1671
- "lstrip": false,
1672
- "normalized": false,
1673
- "rstrip": false,
1674
- "single_word": false,
1675
- "special": false
1676
- },
1677
- "211": {
1678
- "content": "</i>",
1679
- "lstrip": false,
1680
- "normalized": false,
1681
- "rstrip": false,
1682
- "single_word": false,
1683
- "special": false
1684
- },
1685
- "212": {
1686
- "content": "</u>",
1687
- "lstrip": false,
1688
- "normalized": false,
1689
- "rstrip": false,
1690
- "single_word": false,
1691
- "special": false
1692
- },
1693
- "213": {
1694
- "content": "</s>",
1695
- "lstrip": false,
1696
- "normalized": false,
1697
- "rstrip": false,
1698
- "single_word": false,
1699
- "special": true
1700
- },
1701
- "214": {
1702
- "content": "</sub>",
1703
- "lstrip": false,
1704
- "normalized": false,
1705
- "rstrip": false,
1706
- "single_word": false,
1707
- "special": false
1708
- },
1709
- "215": {
1710
- "content": "</sup>",
1711
- "lstrip": false,
1712
- "normalized": false,
1713
- "rstrip": false,
1714
- "single_word": false,
1715
- "special": false
1716
- },
1717
- "216": {
1718
- "content": "</code>",
1719
- "lstrip": false,
1720
- "normalized": false,
1721
- "rstrip": false,
1722
- "single_word": false,
1723
- "special": false
1724
- },
1725
- "255968": {
1726
- "content": "[toxicity=0]",
1727
- "lstrip": false,
1728
- "normalized": false,
1729
- "rstrip": false,
1730
- "single_word": false,
1731
- "special": false
1732
- },
1733
- "255969": {
1734
- "content": "\t\t",
1735
- "lstrip": false,
1736
- "normalized": false,
1737
- "rstrip": false,
1738
- "single_word": false,
1739
- "special": false
1740
- },
1741
- "255970": {
1742
- "content": "\t\t\t",
1743
- "lstrip": false,
1744
- "normalized": false,
1745
- "rstrip": false,
1746
- "single_word": false,
1747
- "special": false
1748
- },
1749
- "255971": {
1750
- "content": "\t\t\t\t",
1751
- "lstrip": false,
1752
- "normalized": false,
1753
- "rstrip": false,
1754
- "single_word": false,
1755
- "special": false
1756
- },
1757
- "255972": {
1758
- "content": "\t\t\t\t\t",
1759
- "lstrip": false,
1760
- "normalized": false,
1761
- "rstrip": false,
1762
- "single_word": false,
1763
- "special": false
1764
- },
1765
- "255973": {
1766
- "content": "\t\t\t\t\t\t",
1767
- "lstrip": false,
1768
- "normalized": false,
1769
- "rstrip": false,
1770
- "single_word": false,
1771
- "special": false
1772
- },
1773
- "255974": {
1774
- "content": "\t\t\t\t\t\t\t",
1775
- "lstrip": false,
1776
- "normalized": false,
1777
- "rstrip": false,
1778
- "single_word": false,
1779
- "special": false
1780
- },
1781
- "255975": {
1782
- "content": "\t\t\t\t\t\t\t\t",
1783
- "lstrip": false,
1784
- "normalized": false,
1785
- "rstrip": false,
1786
- "single_word": false,
1787
- "special": false
1788
- },
1789
- "255976": {
1790
- "content": "\t\t\t\t\t\t\t\t\t",
1791
- "lstrip": false,
1792
- "normalized": false,
1793
- "rstrip": false,
1794
- "single_word": false,
1795
- "special": false
1796
- },
1797
- "255977": {
1798
- "content": "\t\t\t\t\t\t\t\t\t\t",
1799
- "lstrip": false,
1800
- "normalized": false,
1801
- "rstrip": false,
1802
- "single_word": false,
1803
- "special": false
1804
- },
1805
- "255978": {
1806
- "content": "\t\t\t\t\t\t\t\t\t\t\t",
1807
- "lstrip": false,
1808
- "normalized": false,
1809
- "rstrip": false,
1810
- "single_word": false,
1811
- "special": false
1812
- },
1813
- "255979": {
1814
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1815
- "lstrip": false,
1816
- "normalized": false,
1817
- "rstrip": false,
1818
- "single_word": false,
1819
- "special": false
1820
- },
1821
- "255980": {
1822
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1823
- "lstrip": false,
1824
- "normalized": false,
1825
- "rstrip": false,
1826
- "single_word": false,
1827
- "special": false
1828
- },
1829
- "255981": {
1830
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1831
- "lstrip": false,
1832
- "normalized": false,
1833
- "rstrip": false,
1834
- "single_word": false,
1835
- "special": false
1836
- },
1837
- "255982": {
1838
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
- "lstrip": false,
1840
- "normalized": false,
1841
- "rstrip": false,
1842
- "single_word": false,
1843
- "special": false
1844
- },
1845
- "255983": {
1846
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
- "lstrip": false,
1848
- "normalized": false,
1849
- "rstrip": false,
1850
- "single_word": false,
1851
- "special": false
1852
- },
1853
- "255984": {
1854
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
- "lstrip": false,
1856
- "normalized": false,
1857
- "rstrip": false,
1858
- "single_word": false,
1859
- "special": false
1860
- },
1861
- "255985": {
1862
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
- "lstrip": false,
1864
- "normalized": false,
1865
- "rstrip": false,
1866
- "single_word": false,
1867
- "special": false
1868
- },
1869
- "255986": {
1870
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
- "lstrip": false,
1872
- "normalized": false,
1873
- "rstrip": false,
1874
- "single_word": false,
1875
- "special": false
1876
- },
1877
- "255987": {
1878
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
- "lstrip": false,
1880
- "normalized": false,
1881
- "rstrip": false,
1882
- "single_word": false,
1883
- "special": false
1884
- },
1885
- "255988": {
1886
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
- "lstrip": false,
1888
- "normalized": false,
1889
- "rstrip": false,
1890
- "single_word": false,
1891
- "special": false
1892
- },
1893
- "255989": {
1894
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
- "lstrip": false,
1896
- "normalized": false,
1897
- "rstrip": false,
1898
- "single_word": false,
1899
- "special": false
1900
- },
1901
- "255990": {
1902
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
- "lstrip": false,
1904
- "normalized": false,
1905
- "rstrip": false,
1906
- "single_word": false,
1907
- "special": false
1908
- },
1909
- "255991": {
1910
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
- "lstrip": false,
1912
- "normalized": false,
1913
- "rstrip": false,
1914
- "single_word": false,
1915
- "special": false
1916
- },
1917
- "255992": {
1918
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
- "lstrip": false,
1920
- "normalized": false,
1921
- "rstrip": false,
1922
- "single_word": false,
1923
- "special": false
1924
- },
1925
- "255993": {
1926
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
- "lstrip": false,
1928
- "normalized": false,
1929
- "rstrip": false,
1930
- "single_word": false,
1931
- "special": false
1932
- },
1933
- "255994": {
1934
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
- "lstrip": false,
1936
- "normalized": false,
1937
- "rstrip": false,
1938
- "single_word": false,
1939
- "special": false
1940
- },
1941
- "255995": {
1942
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
- "lstrip": false,
1944
- "normalized": false,
1945
- "rstrip": false,
1946
- "single_word": false,
1947
- "special": false
1948
- },
1949
- "255996": {
1950
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
- "lstrip": false,
1952
- "normalized": false,
1953
- "rstrip": false,
1954
- "single_word": false,
1955
- "special": false
1956
- },
1957
- "255997": {
1958
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
- "lstrip": false,
1960
- "normalized": false,
1961
- "rstrip": false,
1962
- "single_word": false,
1963
- "special": false
1964
- },
1965
- "255998": {
1966
- "content": "<eos>",
1967
- "lstrip": false,
1968
- "normalized": false,
1969
- "rstrip": false,
1970
- "single_word": false,
1971
- "special": true
1972
- },
1973
- "255999": {
1974
- "content": "<bos>",
1975
- "lstrip": false,
1976
- "normalized": false,
1977
- "rstrip": false,
1978
- "single_word": false,
1979
- "special": true
1980
- }
1981
- },
1982
  "bos_token": "<s>",
1983
  "clean_up_tokenization_spaces": false,
1984
  "eos_token": "</s>",
1985
- "extra_special_tokens": {},
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1986
  "legacy": null,
 
1987
  "model_max_length": 1000000000000000019884624838656,
1988
  "pad_token": "<pad>",
1989
  "padding_side": "left",
@@ -1993,5 +265,6 @@
1993
  "tokenizer_class": "GemmaTokenizer",
1994
  "unk_token": "<unk>",
1995
  "use_default_system_prompt": false,
1996
- "use_fast": true
 
1997
  }
 
1
  {
2
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": false,
5
  "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<pad>",
8
+ "<eos>",
9
+ "<bos>",
10
+ "<mask>",
11
+ "<2mass>",
12
+ "[@BOS@]",
13
+ "<unused0>",
14
+ "<unused1>",
15
+ "<unused2>",
16
+ "<unused3>",
17
+ "<unused4>",
18
+ "<unused5>",
19
+ "<unused6>",
20
+ "<unused7>",
21
+ "<unused8>",
22
+ "<unused9>",
23
+ "<unused10>",
24
+ "<unused11>",
25
+ "<unused12>",
26
+ "<unused13>",
27
+ "<unused14>",
28
+ "<unused15>",
29
+ "<unused16>",
30
+ "<unused17>",
31
+ "<unused18>",
32
+ "<unused19>",
33
+ "<unused20>",
34
+ "<unused21>",
35
+ "<unused22>",
36
+ "<unused23>",
37
+ "<unused24>",
38
+ "<unused25>",
39
+ "<unused26>",
40
+ "<unused27>",
41
+ "<unused28>",
42
+ "<unused29>",
43
+ "<unused30>",
44
+ "<unused31>",
45
+ "<unused32>",
46
+ "<unused33>",
47
+ "<unused34>",
48
+ "<unused35>",
49
+ "<unused36>",
50
+ "<unused37>",
51
+ "<unused38>",
52
+ "<unused39>",
53
+ "<unused40>",
54
+ "<unused41>",
55
+ "<unused42>",
56
+ "<unused43>",
57
+ "<unused44>",
58
+ "<unused45>",
59
+ "<unused46>",
60
+ "<unused47>",
61
+ "<unused48>",
62
+ "<unused49>",
63
+ "<unused50>",
64
+ "<unused51>",
65
+ "<unused52>",
66
+ "<unused53>",
67
+ "<unused54>",
68
+ "<unused55>",
69
+ "<unused56>",
70
+ "<unused57>",
71
+ "<unused58>",
72
+ "<unused59>",
73
+ "<unused60>",
74
+ "<unused61>",
75
+ "<unused62>",
76
+ "<unused63>",
77
+ "<unused64>",
78
+ "<unused65>",
79
+ "<unused66>",
80
+ "<unused67>",
81
+ "<unused68>",
82
+ "<unused69>",
83
+ "<unused70>",
84
+ "<unused71>",
85
+ "<unused72>",
86
+ "<unused73>",
87
+ "<unused74>",
88
+ "<unused75>",
89
+ "<unused76>",
90
+ "<unused77>",
91
+ "<unused78>",
92
+ "<unused79>",
93
+ "<unused80>",
94
+ "<unused81>",
95
+ "<unused82>",
96
+ "<unused83>",
97
+ "<unused84>",
98
+ "<unused85>",
99
+ "<unused86>",
100
+ "<unused87>",
101
+ "<unused88>",
102
+ "<unused89>",
103
+ "<unused90>",
104
+ "<unused91>",
105
+ "<unused92>",
106
+ "<unused93>",
107
+ "<unused94>",
108
+ "<unused95>",
109
+ "<unused96>",
110
+ "<unused97>",
111
+ "<unused98>",
112
+ "<start_of_turn>",
113
+ "<end_of_turn>",
114
+ "\n",
115
+ "\n\n",
116
+ "\n\n\n",
117
+ "\n\n\n\n",
118
+ "\n\n\n\n\n",
119
+ "\n\n\n\n\n\n",
120
+ "\n\n\n\n\n\n\n",
121
+ "\n\n\n\n\n\n\n\n",
122
+ "\n\n\n\n\n\n\n\n\n",
123
+ "\n\n\n\n\n\n\n\n\n\n",
124
+ "\n\n\n\n\n\n\n\n\n\n\n",
125
+ "\n\n\n\n\n\n\n\n\n\n\n\n",
126
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n",
127
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
128
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
129
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
130
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
131
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
132
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
133
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
134
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
135
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
136
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
137
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
138
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
139
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
140
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
141
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
142
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
143
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
144
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
145
+ "▁▁",
146
+ "▁▁▁",
147
+ "▁▁▁▁",
148
+ "▁▁▁▁▁",
149
+ "▁▁▁▁▁▁",
150
+ "▁▁▁▁▁▁▁",
151
+ "▁▁▁▁▁▁▁▁",
152
+ "▁▁▁▁▁▁▁▁▁",
153
+ "▁▁▁▁▁▁▁▁▁▁",
154
+ "▁▁▁▁▁▁▁▁▁▁▁",
155
+ "▁▁▁▁▁▁▁▁▁▁▁▁",
156
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁",
157
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
158
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
159
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
160
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
161
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
162
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
163
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
164
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
165
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
166
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
167
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
168
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
169
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
170
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
171
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
172
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
173
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
174
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
175
+ "<table>",
176
+ "<caption>",
177
+ "<thead>",
178
+ "<tbody>",
179
+ "<tfoot>",
180
+ "<tr>",
181
+ "<th>",
182
+ "<td>",
183
+ "</table>",
184
+ "</caption>",
185
+ "</thead>",
186
+ "</tbody>",
187
+ "</tfoot>",
188
+ "</tr>",
189
+ "</th>",
190
+ "</td>",
191
+ "<h1>",
192
+ "<h2>",
193
+ "<h3>",
194
+ "<h4>",
195
+ "<h5>",
196
+ "<h6>",
197
+ "<blockquote>",
198
+ "</h1>",
199
+ "</h2>",
200
+ "</h3>",
201
+ "</h4>",
202
+ "</h5>",
203
+ "</h6>",
204
+ "</blockquote>",
205
+ "<strong>",
206
+ "<em>",
207
+ "<b>",
208
+ "<i>",
209
+ "<u>",
210
+ "<s>",
211
+ "<sub>",
212
+ "<sup>",
213
+ "<code>",
214
+ "</strong>",
215
+ "</em>",
216
+ "</b>",
217
+ "</i>",
218
+ "</u>",
219
+ "</s>",
220
+ "</sub>",
221
+ "</sup>",
222
+ "</code>",
223
+ "[toxicity=0]",
224
+ "\t\t",
225
+ "\t\t\t",
226
+ "\t\t\t\t",
227
+ "\t\t\t\t\t",
228
+ "\t\t\t\t\t\t",
229
+ "\t\t\t\t\t\t\t",
230
+ "\t\t\t\t\t\t\t\t",
231
+ "\t\t\t\t\t\t\t\t\t",
232
+ "\t\t\t\t\t\t\t\t\t\t",
233
+ "\t\t\t\t\t\t\t\t\t\t\t",
234
+ "\t\t\t\t\t\t\t\t\t\t\t\t",
235
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t",
236
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
237
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
238
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
239
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
240
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
241
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
242
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
243
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
244
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
245
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
246
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
247
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
248
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
249
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
250
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
251
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
252
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
253
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
254
+ "<unused99>"
255
+ ],
256
+ "is_local": false,
257
  "legacy": null,
258
+ "mask_token": "<mask>",
259
  "model_max_length": 1000000000000000019884624838656,
260
  "pad_token": "<pad>",
261
  "padding_side": "left",
 
265
  "tokenizer_class": "GemmaTokenizer",
266
  "unk_token": "<unk>",
267
  "use_default_system_prompt": false,
268
+ "use_fast": true,
269
+ "vocab_file": "/root/.cache/huggingface/hub/models--CryptoYogi--gemma-2b-tamil-base/snapshots/a5d209a58b1290c30cbdbee7647758d56280a189/tokenizer.model"
270
  }