ykhwang commited on
Commit
53c8d7b
1 Parent(s): a72bf57

Patch for tokenizer

Browse files

Added sentinel tokens for resolving tokenizer issues on GGUF conversion.
Seel also: https://huggingface.co/42dot/42dot_LLM-SFT-1.3B/discussions/2

Files changed (4) hide show
  1. added_tokens.json +44 -4
  2. special_tokens_map.json +46 -0
  3. tokenizer.json +444 -6
  4. vocab.json +0 -0
added_tokens.json CHANGED
@@ -1,6 +1,46 @@
1
  {
2
- "<|endoftext|>": 50256,
3
- "<||bos||>": 50257,
4
- "<||pad||>": 50258,
5
- "<||unk||>": 50259
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "<||unused10||>": 50269,
3
+ "<||unused11||>": 50270,
4
+ "<||unused12||>": 50271,
5
+ "<||unused13||>": 50272,
6
+ "<||unused14||>": 50273,
7
+ "<||unused15||>": 50274,
8
+ "<||unused16||>": 50275,
9
+ "<||unused17||>": 50276,
10
+ "<||unused18||>": 50277,
11
+ "<||unused19||>": 50278,
12
+ "<||unused1||>": 50260,
13
+ "<||unused20||>": 50279,
14
+ "<||unused21||>": 50280,
15
+ "<||unused22||>": 50281,
16
+ "<||unused23||>": 50282,
17
+ "<||unused24||>": 50283,
18
+ "<||unused25||>": 50284,
19
+ "<||unused26||>": 50285,
20
+ "<||unused27||>": 50286,
21
+ "<||unused28||>": 50287,
22
+ "<||unused29||>": 50288,
23
+ "<||unused2||>": 50261,
24
+ "<||unused30||>": 50289,
25
+ "<||unused31||>": 50290,
26
+ "<||unused32||>": 50291,
27
+ "<||unused33||>": 50292,
28
+ "<||unused34||>": 50293,
29
+ "<||unused35||>": 50294,
30
+ "<||unused36||>": 50295,
31
+ "<||unused37||>": 50296,
32
+ "<||unused38||>": 50297,
33
+ "<||unused39||>": 50298,
34
+ "<||unused3||>": 50262,
35
+ "<||unused40||>": 50299,
36
+ "<||unused41||>": 50300,
37
+ "<||unused42||>": 50301,
38
+ "<||unused43||>": 50302,
39
+ "<||unused44||>": 50303,
40
+ "<||unused4||>": 50263,
41
+ "<||unused5||>": 50264,
42
+ "<||unused6||>": 50265,
43
+ "<||unused7||>": 50266,
44
+ "<||unused8||>": 50267,
45
+ "<||unused9||>": 50268
46
  }
special_tokens_map.json CHANGED
@@ -1,4 +1,50 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<||bos||>",
3
  "eos_token": {
4
  "content": "<|endoftext|>",
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<||unused1||>",
4
+ "<||unused2||>",
5
+ "<||unused3||>",
6
+ "<||unused4||>",
7
+ "<||unused5||>",
8
+ "<||unused6||>",
9
+ "<||unused7||>",
10
+ "<||unused8||>",
11
+ "<||unused9||>",
12
+ "<||unused10||>",
13
+ "<||unused11||>",
14
+ "<||unused12||>",
15
+ "<||unused13||>",
16
+ "<||unused14||>",
17
+ "<||unused15||>",
18
+ "<||unused16||>",
19
+ "<||unused17||>",
20
+ "<||unused18||>",
21
+ "<||unused19||>",
22
+ "<||unused20||>",
23
+ "<||unused21||>",
24
+ "<||unused22||>",
25
+ "<||unused23||>",
26
+ "<||unused24||>",
27
+ "<||unused25||>",
28
+ "<||unused26||>",
29
+ "<||unused27||>",
30
+ "<||unused28||>",
31
+ "<||unused29||>",
32
+ "<||unused30||>",
33
+ "<||unused31||>",
34
+ "<||unused32||>",
35
+ "<||unused33||>",
36
+ "<||unused34||>",
37
+ "<||unused35||>",
38
+ "<||unused36||>",
39
+ "<||unused37||>",
40
+ "<||unused38||>",
41
+ "<||unused39||>",
42
+ "<||unused40||>",
43
+ "<||unused41||>",
44
+ "<||unused42||>",
45
+ "<||unused43||>",
46
+ "<||unused44||>"
47
+ ],
48
  "bos_token": "<||bos||>",
49
  "eos_token": {
50
  "content": "<|endoftext|>",
tokenizer.json CHANGED
@@ -38,6 +38,402 @@
38
  "rstrip": false,
39
  "normalized": false,
40
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  }
42
  ],
43
  "normalizer": null,
@@ -48,10 +444,52 @@
48
  "use_regex": true
49
  },
50
  "post_processor": {
51
- "type": "ByteLevel",
52
- "add_prefix_space": true,
53
- "trim_offsets": true,
54
- "use_regex": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  },
56
  "decoder": {
57
  "type": "ByteLevel",
@@ -63,8 +501,8 @@
63
  "type": "BPE",
64
  "dropout": null,
65
  "unk_token": null,
66
- "continuing_subword_prefix": null,
67
- "end_of_word_suffix": null,
68
  "fuse_unk": false,
69
  "byte_fallback": false,
70
  "vocab": {
 
38
  "rstrip": false,
39
  "normalized": false,
40
  "special": true
41
+ },
42
+ {
43
+ "id": 50260,
44
+ "content": "<||unused1||>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 50261,
53
+ "content": "<||unused2||>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 50262,
62
+ "content": "<||unused3||>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 50263,
71
+ "content": "<||unused4||>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 50264,
80
+ "content": "<||unused5||>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 50265,
89
+ "content": "<||unused6||>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 50266,
98
+ "content": "<||unused7||>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 50267,
107
+ "content": "<||unused8||>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 50268,
116
+ "content": "<||unused9||>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 50269,
125
+ "content": "<||unused10||>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 50270,
134
+ "content": "<||unused11||>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 50271,
143
+ "content": "<||unused12||>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 50272,
152
+ "content": "<||unused13||>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 50273,
161
+ "content": "<||unused14||>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 50274,
170
+ "content": "<||unused15||>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 50275,
179
+ "content": "<||unused16||>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 50276,
188
+ "content": "<||unused17||>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 50277,
197
+ "content": "<||unused18||>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 50278,
206
+ "content": "<||unused19||>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 50279,
215
+ "content": "<||unused20||>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 50280,
224
+ "content": "<||unused21||>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 50281,
233
+ "content": "<||unused22||>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 50282,
242
+ "content": "<||unused23||>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 50283,
251
+ "content": "<||unused24||>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 50284,
260
+ "content": "<||unused25||>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 50285,
269
+ "content": "<||unused26||>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 50286,
278
+ "content": "<||unused27||>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 50287,
287
+ "content": "<||unused28||>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 50288,
296
+ "content": "<||unused29||>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 50289,
305
+ "content": "<||unused30||>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 50290,
314
+ "content": "<||unused31||>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 50291,
323
+ "content": "<||unused32||>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 50292,
332
+ "content": "<||unused33||>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 50293,
341
+ "content": "<||unused34||>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 50294,
350
+ "content": "<||unused35||>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 50295,
359
+ "content": "<||unused36||>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 50296,
368
+ "content": "<||unused37||>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 50297,
377
+ "content": "<||unused38||>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 50298,
386
+ "content": "<||unused39||>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 50299,
395
+ "content": "<||unused40||>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 50300,
404
+ "content": "<||unused41||>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 50301,
413
+ "content": "<||unused42||>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 50302,
422
+ "content": "<||unused43||>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 50303,
431
+ "content": "<||unused44||>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
  }
438
  ],
439
  "normalizer": null,
 
444
  "use_regex": true
445
  },
446
  "post_processor": {
447
+ "type": "TemplateProcessing",
448
+ "single": [
449
+ {
450
+ "SpecialToken": {
451
+ "id": "<||bos||>",
452
+ "type_id": 0
453
+ }
454
+ },
455
+ {
456
+ "Sequence": {
457
+ "id": "A",
458
+ "type_id": 0
459
+ }
460
+ }
461
+ ],
462
+ "pair": [
463
+ {
464
+ "SpecialToken": {
465
+ "id": "<||bos||>",
466
+ "type_id": 0
467
+ }
468
+ },
469
+ {
470
+ "Sequence": {
471
+ "id": "A",
472
+ "type_id": 0
473
+ }
474
+ },
475
+ {
476
+ "Sequence": {
477
+ "id": "B",
478
+ "type_id": 1
479
+ }
480
+ }
481
+ ],
482
+ "special_tokens": {
483
+ "<||bos||>": {
484
+ "id": "<||bos||>",
485
+ "ids": [
486
+ 50257
487
+ ],
488
+ "tokens": [
489
+ "<||bos||>"
490
+ ]
491
+ }
492
+ }
493
  },
494
  "decoder": {
495
  "type": "ByteLevel",
 
501
  "type": "BPE",
502
  "dropout": null,
503
  "unk_token": null,
504
+ "continuing_subword_prefix": "",
505
+ "end_of_word_suffix": "",
506
  "fuse_unk": false,
507
  "byte_fallback": false,
508
  "vocab": {
vocab.json CHANGED
The diff for this file is too large to render. See raw diff