Konnmjn commited on
Commit
57c52f0
·
verified ·
1 Parent(s): 3a58097

Upload tokenizer

Browse files
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[SpeechStart]",
4
+ "[SpeechEnd]",
5
+ "[TextStart]",
6
+ "[TextEnd]"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,915 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "38365": {
31
+ "content": "<<SYS>>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "38366": {
39
+ "content": "<</SYS>>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "38367": {
47
+ "content": "[INST]",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "38368": {
55
+ "content": "[/INST]",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "38369": {
63
+ "content": "[HUBERT_0]",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "38370": {
71
+ "content": "[HUBERT_1]",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "38371": {
79
+ "content": "[HUBERT_2]",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "38372": {
87
+ "content": "[HUBERT_3]",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "38373": {
95
+ "content": "[HUBERT_4]",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "38374": {
103
+ "content": "[HUBERT_5]",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "38375": {
111
+ "content": "[HUBERT_6]",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "38376": {
119
+ "content": "[HUBERT_7]",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "38377": {
127
+ "content": "[HUBERT_8]",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "38378": {
135
+ "content": "[HUBERT_9]",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "38379": {
143
+ "content": "[HUBERT_10]",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "38380": {
151
+ "content": "[HUBERT_11]",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "38381": {
159
+ "content": "[HUBERT_12]",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "38382": {
167
+ "content": "[HUBERT_13]",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "38383": {
175
+ "content": "[HUBERT_14]",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "38384": {
183
+ "content": "[HUBERT_15]",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "38385": {
191
+ "content": "[HUBERT_16]",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "38386": {
199
+ "content": "[HUBERT_17]",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "38387": {
207
+ "content": "[HUBERT_18]",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "38388": {
215
+ "content": "[HUBERT_19]",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "38389": {
223
+ "content": "[HUBERT_20]",
224
+ "lstrip": false,
225
+ "normalized": true,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "38390": {
231
+ "content": "[HUBERT_21]",
232
+ "lstrip": false,
233
+ "normalized": true,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "38391": {
239
+ "content": "[HUBERT_22]",
240
+ "lstrip": false,
241
+ "normalized": true,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "38392": {
247
+ "content": "[HUBERT_23]",
248
+ "lstrip": false,
249
+ "normalized": true,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "38393": {
255
+ "content": "[HUBERT_24]",
256
+ "lstrip": false,
257
+ "normalized": true,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "38394": {
263
+ "content": "[HUBERT_25]",
264
+ "lstrip": false,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "38395": {
271
+ "content": "[HUBERT_26]",
272
+ "lstrip": false,
273
+ "normalized": true,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "38396": {
279
+ "content": "[HUBERT_27]",
280
+ "lstrip": false,
281
+ "normalized": true,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "38397": {
287
+ "content": "[HUBERT_28]",
288
+ "lstrip": false,
289
+ "normalized": true,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "38398": {
295
+ "content": "[HUBERT_29]",
296
+ "lstrip": false,
297
+ "normalized": true,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ },
302
+ "38399": {
303
+ "content": "[HUBERT_30]",
304
+ "lstrip": false,
305
+ "normalized": true,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false
309
+ },
310
+ "38400": {
311
+ "content": "[HUBERT_31]",
312
+ "lstrip": false,
313
+ "normalized": true,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": false
317
+ },
318
+ "38401": {
319
+ "content": "[HUBERT_32]",
320
+ "lstrip": false,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": false
325
+ },
326
+ "38402": {
327
+ "content": "[HUBERT_33]",
328
+ "lstrip": false,
329
+ "normalized": true,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": false
333
+ },
334
+ "38403": {
335
+ "content": "[HUBERT_34]",
336
+ "lstrip": false,
337
+ "normalized": true,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": false
341
+ },
342
+ "38404": {
343
+ "content": "[HUBERT_35]",
344
+ "lstrip": false,
345
+ "normalized": true,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": false
349
+ },
350
+ "38405": {
351
+ "content": "[HUBERT_36]",
352
+ "lstrip": false,
353
+ "normalized": true,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": false
357
+ },
358
+ "38406": {
359
+ "content": "[HUBERT_37]",
360
+ "lstrip": false,
361
+ "normalized": true,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": false
365
+ },
366
+ "38407": {
367
+ "content": "[HUBERT_38]",
368
+ "lstrip": false,
369
+ "normalized": true,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": false
373
+ },
374
+ "38408": {
375
+ "content": "[HUBERT_39]",
376
+ "lstrip": false,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": false
381
+ },
382
+ "38409": {
383
+ "content": "[HUBERT_40]",
384
+ "lstrip": false,
385
+ "normalized": true,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": false
389
+ },
390
+ "38410": {
391
+ "content": "[HUBERT_41]",
392
+ "lstrip": false,
393
+ "normalized": true,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": false
397
+ },
398
+ "38411": {
399
+ "content": "[HUBERT_42]",
400
+ "lstrip": false,
401
+ "normalized": true,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": false
405
+ },
406
+ "38412": {
407
+ "content": "[HUBERT_43]",
408
+ "lstrip": false,
409
+ "normalized": true,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": false
413
+ },
414
+ "38413": {
415
+ "content": "[HUBERT_44]",
416
+ "lstrip": false,
417
+ "normalized": true,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": false
421
+ },
422
+ "38414": {
423
+ "content": "[HUBERT_45]",
424
+ "lstrip": false,
425
+ "normalized": true,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": false
429
+ },
430
+ "38415": {
431
+ "content": "[HUBERT_46]",
432
+ "lstrip": false,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": false
437
+ },
438
+ "38416": {
439
+ "content": "[HUBERT_47]",
440
+ "lstrip": false,
441
+ "normalized": true,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": false
445
+ },
446
+ "38417": {
447
+ "content": "[HUBERT_48]",
448
+ "lstrip": false,
449
+ "normalized": true,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": false
453
+ },
454
+ "38418": {
455
+ "content": "[HUBERT_49]",
456
+ "lstrip": false,
457
+ "normalized": true,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": false
461
+ },
462
+ "38419": {
463
+ "content": "[HUBERT_50]",
464
+ "lstrip": false,
465
+ "normalized": true,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": false
469
+ },
470
+ "38420": {
471
+ "content": "[HUBERT_51]",
472
+ "lstrip": false,
473
+ "normalized": true,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": false
477
+ },
478
+ "38421": {
479
+ "content": "[HUBERT_52]",
480
+ "lstrip": false,
481
+ "normalized": true,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": false
485
+ },
486
+ "38422": {
487
+ "content": "[HUBERT_53]",
488
+ "lstrip": false,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": false
493
+ },
494
+ "38423": {
495
+ "content": "[HUBERT_54]",
496
+ "lstrip": false,
497
+ "normalized": true,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": false
501
+ },
502
+ "38424": {
503
+ "content": "[HUBERT_55]",
504
+ "lstrip": false,
505
+ "normalized": true,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": false
509
+ },
510
+ "38425": {
511
+ "content": "[HUBERT_56]",
512
+ "lstrip": false,
513
+ "normalized": true,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": false
517
+ },
518
+ "38426": {
519
+ "content": "[HUBERT_57]",
520
+ "lstrip": false,
521
+ "normalized": true,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": false
525
+ },
526
+ "38427": {
527
+ "content": "[HUBERT_58]",
528
+ "lstrip": false,
529
+ "normalized": true,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": false
533
+ },
534
+ "38428": {
535
+ "content": "[HUBERT_59]",
536
+ "lstrip": false,
537
+ "normalized": true,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": false
541
+ },
542
+ "38429": {
543
+ "content": "[HUBERT_60]",
544
+ "lstrip": false,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": false
549
+ },
550
+ "38430": {
551
+ "content": "[HUBERT_61]",
552
+ "lstrip": false,
553
+ "normalized": true,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": false
557
+ },
558
+ "38431": {
559
+ "content": "[HUBERT_62]",
560
+ "lstrip": false,
561
+ "normalized": true,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": false
565
+ },
566
+ "38432": {
567
+ "content": "[HUBERT_63]",
568
+ "lstrip": false,
569
+ "normalized": true,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": false
573
+ },
574
+ "38433": {
575
+ "content": "[HUBERT_64]",
576
+ "lstrip": false,
577
+ "normalized": true,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": false
581
+ },
582
+ "38434": {
583
+ "content": "[HUBERT_65]",
584
+ "lstrip": false,
585
+ "normalized": true,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": false
589
+ },
590
+ "38435": {
591
+ "content": "[HUBERT_66]",
592
+ "lstrip": false,
593
+ "normalized": true,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": false
597
+ },
598
+ "38436": {
599
+ "content": "[HUBERT_67]",
600
+ "lstrip": false,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": false
605
+ },
606
+ "38437": {
607
+ "content": "[HUBERT_68]",
608
+ "lstrip": false,
609
+ "normalized": true,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": false
613
+ },
614
+ "38438": {
615
+ "content": "[HUBERT_69]",
616
+ "lstrip": false,
617
+ "normalized": true,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": false
621
+ },
622
+ "38439": {
623
+ "content": "[HUBERT_70]",
624
+ "lstrip": false,
625
+ "normalized": true,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": false
629
+ },
630
+ "38440": {
631
+ "content": "[HUBERT_71]",
632
+ "lstrip": false,
633
+ "normalized": true,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": false
637
+ },
638
+ "38441": {
639
+ "content": "[HUBERT_72]",
640
+ "lstrip": false,
641
+ "normalized": true,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": false
645
+ },
646
+ "38442": {
647
+ "content": "[HUBERT_73]",
648
+ "lstrip": false,
649
+ "normalized": true,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": false
653
+ },
654
+ "38443": {
655
+ "content": "[HUBERT_74]",
656
+ "lstrip": false,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": false
661
+ },
662
+ "38444": {
663
+ "content": "[HUBERT_75]",
664
+ "lstrip": false,
665
+ "normalized": true,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": false
669
+ },
670
+ "38445": {
671
+ "content": "[HUBERT_76]",
672
+ "lstrip": false,
673
+ "normalized": true,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": false
677
+ },
678
+ "38446": {
679
+ "content": "[HUBERT_77]",
680
+ "lstrip": false,
681
+ "normalized": true,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": false
685
+ },
686
+ "38447": {
687
+ "content": "[HUBERT_78]",
688
+ "lstrip": false,
689
+ "normalized": true,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": false
693
+ },
694
+ "38448": {
695
+ "content": "[HUBERT_79]",
696
+ "lstrip": false,
697
+ "normalized": true,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": false
701
+ },
702
+ "38449": {
703
+ "content": "[HUBERT_80]",
704
+ "lstrip": false,
705
+ "normalized": true,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": false
709
+ },
710
+ "38450": {
711
+ "content": "[HUBERT_81]",
712
+ "lstrip": false,
713
+ "normalized": true,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": false
717
+ },
718
+ "38451": {
719
+ "content": "[HUBERT_82]",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": false
725
+ },
726
+ "38452": {
727
+ "content": "[HUBERT_83]",
728
+ "lstrip": false,
729
+ "normalized": true,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": false
733
+ },
734
+ "38453": {
735
+ "content": "[HUBERT_84]",
736
+ "lstrip": false,
737
+ "normalized": true,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": false
741
+ },
742
+ "38454": {
743
+ "content": "[HUBERT_85]",
744
+ "lstrip": false,
745
+ "normalized": true,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": false
749
+ },
750
+ "38455": {
751
+ "content": "[HUBERT_86]",
752
+ "lstrip": false,
753
+ "normalized": true,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": false
757
+ },
758
+ "38456": {
759
+ "content": "[HUBERT_87]",
760
+ "lstrip": false,
761
+ "normalized": true,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": false
765
+ },
766
+ "38457": {
767
+ "content": "[HUBERT_88]",
768
+ "lstrip": false,
769
+ "normalized": true,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": false
773
+ },
774
+ "38458": {
775
+ "content": "[HUBERT_89]",
776
+ "lstrip": false,
777
+ "normalized": true,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": false
781
+ },
782
+ "38459": {
783
+ "content": "[HUBERT_90]",
784
+ "lstrip": false,
785
+ "normalized": true,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": false
789
+ },
790
+ "38460": {
791
+ "content": "[HUBERT_91]",
792
+ "lstrip": false,
793
+ "normalized": true,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": false
797
+ },
798
+ "38461": {
799
+ "content": "[HUBERT_92]",
800
+ "lstrip": false,
801
+ "normalized": true,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": false
805
+ },
806
+ "38462": {
807
+ "content": "[HUBERT_93]",
808
+ "lstrip": false,
809
+ "normalized": true,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": false
813
+ },
814
+ "38463": {
815
+ "content": "[HUBERT_94]",
816
+ "lstrip": false,
817
+ "normalized": true,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": false
821
+ },
822
+ "38464": {
823
+ "content": "[HUBERT_95]",
824
+ "lstrip": false,
825
+ "normalized": true,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": false
829
+ },
830
+ "38465": {
831
+ "content": "[HUBERT_96]",
832
+ "lstrip": false,
833
+ "normalized": true,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": false
837
+ },
838
+ "38466": {
839
+ "content": "[HUBERT_97]",
840
+ "lstrip": false,
841
+ "normalized": true,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": false
845
+ },
846
+ "38467": {
847
+ "content": "[HUBERT_98]",
848
+ "lstrip": false,
849
+ "normalized": true,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": false
853
+ },
854
+ "38468": {
855
+ "content": "[HUBERT_99]",
856
+ "lstrip": false,
857
+ "normalized": true,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": false
861
+ },
862
+ "38469": {
863
+ "content": "[SpeechStart]",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "38470": {
871
+ "content": "[SpeechEnd]",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "38471": {
879
+ "content": "[TextStart]",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "38472": {
887
+ "content": "[TextEnd]",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ }
894
+ },
895
+ "additional_special_tokens": [
896
+ "[SpeechStart]",
897
+ "[SpeechEnd]",
898
+ "[TextStart]",
899
+ "[TextEnd]"
900
+ ],
901
+ "bos_token": "<s>",
902
+ "clean_up_tokenization_spaces": false,
903
+ "eos_token": "</s>",
904
+ "extra_special_tokens": {},
905
+ "legacy": true,
906
+ "model_max_length": 32768,
907
+ "pad_token": "<unk>",
908
+ "padding_side": "right",
909
+ "sp_model_kwargs": {},
910
+ "spaces_between_special_tokens": false,
911
+ "tokenizer_class": "LlamaTokenizer",
912
+ "unk_token": "<unk>",
913
+ "use_default_system_prompt": false,
914
+ "use_fast": true
915
+ }