Clemylia commited on
Commit
ac0227c
·
verified ·
1 Parent(s): 2b28d6b

Ajout du tokenizer associé au modèle final

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +37 -0
  2. tokenizer.json +626 -0
  3. tokenizer_config.json +53 -0
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,626 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<s>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<mask>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "ByteLevel",
55
+ "add_prefix_space": false,
56
+ "trim_offsets": true,
57
+ "use_regex": true
58
+ },
59
+ "post_processor": {
60
+ "type": "ByteLevel",
61
+ "add_prefix_space": true,
62
+ "trim_offsets": false,
63
+ "use_regex": true
64
+ },
65
+ "decoder": {
66
+ "type": "ByteLevel",
67
+ "add_prefix_space": true,
68
+ "trim_offsets": true,
69
+ "use_regex": true
70
+ },
71
+ "model": {
72
+ "type": "BPE",
73
+ "dropout": null,
74
+ "unk_token": null,
75
+ "continuing_subword_prefix": null,
76
+ "end_of_word_suffix": null,
77
+ "fuse_unk": false,
78
+ "byte_fallback": false,
79
+ "ignore_merges": false,
80
+ "vocab": {
81
+ "<s>": 0,
82
+ "<pad>": 1,
83
+ "</s>": 2,
84
+ "<unk>": 3,
85
+ "<mask>": 4,
86
+ "!": 5,
87
+ "\"": 6,
88
+ "#": 7,
89
+ "$": 8,
90
+ "%": 9,
91
+ "&": 10,
92
+ "'": 11,
93
+ "(": 12,
94
+ ")": 13,
95
+ "*": 14,
96
+ "+": 15,
97
+ ",": 16,
98
+ "-": 17,
99
+ ".": 18,
100
+ "/": 19,
101
+ "0": 20,
102
+ "1": 21,
103
+ "2": 22,
104
+ "3": 23,
105
+ "4": 24,
106
+ "5": 25,
107
+ "6": 26,
108
+ "7": 27,
109
+ "8": 28,
110
+ "9": 29,
111
+ ":": 30,
112
+ ";": 31,
113
+ "<": 32,
114
+ "=": 33,
115
+ ">": 34,
116
+ "?": 35,
117
+ "@": 36,
118
+ "A": 37,
119
+ "B": 38,
120
+ "C": 39,
121
+ "D": 40,
122
+ "E": 41,
123
+ "F": 42,
124
+ "G": 43,
125
+ "H": 44,
126
+ "I": 45,
127
+ "J": 46,
128
+ "K": 47,
129
+ "L": 48,
130
+ "M": 49,
131
+ "N": 50,
132
+ "O": 51,
133
+ "P": 52,
134
+ "Q": 53,
135
+ "R": 54,
136
+ "S": 55,
137
+ "T": 56,
138
+ "U": 57,
139
+ "V": 58,
140
+ "W": 59,
141
+ "X": 60,
142
+ "Y": 61,
143
+ "Z": 62,
144
+ "[": 63,
145
+ "\\": 64,
146
+ "]": 65,
147
+ "^": 66,
148
+ "_": 67,
149
+ "`": 68,
150
+ "a": 69,
151
+ "b": 70,
152
+ "c": 71,
153
+ "d": 72,
154
+ "e": 73,
155
+ "f": 74,
156
+ "g": 75,
157
+ "h": 76,
158
+ "i": 77,
159
+ "j": 78,
160
+ "k": 79,
161
+ "l": 80,
162
+ "m": 81,
163
+ "n": 82,
164
+ "o": 83,
165
+ "p": 84,
166
+ "q": 85,
167
+ "r": 86,
168
+ "s": 87,
169
+ "t": 88,
170
+ "u": 89,
171
+ "v": 90,
172
+ "w": 91,
173
+ "x": 92,
174
+ "y": 93,
175
+ "z": 94,
176
+ "{": 95,
177
+ "|": 96,
178
+ "}": 97,
179
+ "~": 98,
180
+ "¡": 99,
181
+ "¢": 100,
182
+ "£": 101,
183
+ "¤": 102,
184
+ "¥": 103,
185
+ "¦": 104,
186
+ "§": 105,
187
+ "¨": 106,
188
+ "©": 107,
189
+ "ª": 108,
190
+ "«": 109,
191
+ "¬": 110,
192
+ "®": 111,
193
+ "¯": 112,
194
+ "°": 113,
195
+ "±": 114,
196
+ "²": 115,
197
+ "³": 116,
198
+ "´": 117,
199
+ "µ": 118,
200
+ "¶": 119,
201
+ "·": 120,
202
+ "¸": 121,
203
+ "¹": 122,
204
+ "º": 123,
205
+ "»": 124,
206
+ "¼": 125,
207
+ "½": 126,
208
+ "¾": 127,
209
+ "¿": 128,
210
+ "À": 129,
211
+ "Á": 130,
212
+ "Â": 131,
213
+ "Ã": 132,
214
+ "Ä": 133,
215
+ "Å": 134,
216
+ "Æ": 135,
217
+ "Ç": 136,
218
+ "È": 137,
219
+ "É": 138,
220
+ "Ê": 139,
221
+ "Ë": 140,
222
+ "Ì": 141,
223
+ "Í": 142,
224
+ "Î": 143,
225
+ "Ï": 144,
226
+ "Ð": 145,
227
+ "Ñ": 146,
228
+ "Ò": 147,
229
+ "Ó": 148,
230
+ "Ô": 149,
231
+ "Õ": 150,
232
+ "Ö": 151,
233
+ "×": 152,
234
+ "Ø": 153,
235
+ "Ù": 154,
236
+ "Ú": 155,
237
+ "Û": 156,
238
+ "Ü": 157,
239
+ "Ý": 158,
240
+ "Þ": 159,
241
+ "ß": 160,
242
+ "à": 161,
243
+ "á": 162,
244
+ "â": 163,
245
+ "ã": 164,
246
+ "ä": 165,
247
+ "å": 166,
248
+ "æ": 167,
249
+ "ç": 168,
250
+ "è": 169,
251
+ "é": 170,
252
+ "ê": 171,
253
+ "ë": 172,
254
+ "ì": 173,
255
+ "í": 174,
256
+ "î": 175,
257
+ "ï": 176,
258
+ "ð": 177,
259
+ "ñ": 178,
260
+ "ò": 179,
261
+ "ó": 180,
262
+ "ô": 181,
263
+ "õ": 182,
264
+ "ö": 183,
265
+ "÷": 184,
266
+ "ø": 185,
267
+ "ù": 186,
268
+ "ú": 187,
269
+ "û": 188,
270
+ "ü": 189,
271
+ "ý": 190,
272
+ "þ": 191,
273
+ "ÿ": 192,
274
+ "Ā": 193,
275
+ "ā": 194,
276
+ "Ă": 195,
277
+ "ă": 196,
278
+ "Ą": 197,
279
+ "ą": 198,
280
+ "Ć": 199,
281
+ "ć": 200,
282
+ "Ĉ": 201,
283
+ "ĉ": 202,
284
+ "Ċ": 203,
285
+ "ċ": 204,
286
+ "Č": 205,
287
+ "č": 206,
288
+ "Ď": 207,
289
+ "ď": 208,
290
+ "Đ": 209,
291
+ "đ": 210,
292
+ "Ē": 211,
293
+ "ē": 212,
294
+ "Ĕ": 213,
295
+ "ĕ": 214,
296
+ "Ė": 215,
297
+ "ė": 216,
298
+ "Ę": 217,
299
+ "ę": 218,
300
+ "Ě": 219,
301
+ "ě": 220,
302
+ "Ĝ": 221,
303
+ "ĝ": 222,
304
+ "Ğ": 223,
305
+ "ğ": 224,
306
+ "Ġ": 225,
307
+ "ġ": 226,
308
+ "Ģ": 227,
309
+ "ģ": 228,
310
+ "Ĥ": 229,
311
+ "ĥ": 230,
312
+ "Ħ": 231,
313
+ "ħ": 232,
314
+ "Ĩ": 233,
315
+ "ĩ": 234,
316
+ "Ī": 235,
317
+ "ī": 236,
318
+ "Ĭ": 237,
319
+ "ĭ": 238,
320
+ "Į": 239,
321
+ "į": 240,
322
+ "İ": 241,
323
+ "ı": 242,
324
+ "IJ": 243,
325
+ "ij": 244,
326
+ "Ĵ": 245,
327
+ "ĵ": 246,
328
+ "Ķ": 247,
329
+ "ķ": 248,
330
+ "ĸ": 249,
331
+ "Ĺ": 250,
332
+ "ĺ": 251,
333
+ "Ļ": 252,
334
+ "ļ": 253,
335
+ "Ľ": 254,
336
+ "ľ": 255,
337
+ "Ŀ": 256,
338
+ "ŀ": 257,
339
+ "Ł": 258,
340
+ "ł": 259,
341
+ "Ń": 260,
342
+ "ik": 261,
343
+ "ika": 262,
344
+ "Pika": 263,
345
+ "Ġ?": 264,
346
+ "..": 265,
347
+ "hu": 266,
348
+ "Ġp": 267,
349
+ "chu": 268,
350
+ "Ġ!": 269,
351
+ "Ġpika": 270,
352
+ "es": 271,
353
+ "Tu": 272,
354
+ "ou": 273,
355
+ "...": 274,
356
+ "Qu": 275,
357
+ "eu": 276,
358
+ "Ġv": 277,
359
+ "Ġchu": 278,
360
+ "Ġes": 279,
361
+ "Pikachu": 280,
362
+ "as": 281,
363
+ "en": 282,
364
+ "oi": 283,
365
+ "pika": 284,
366
+ "tu": 285,
367
+ "é": 286,
368
+ "Ġf": 287,
369
+ "Ġt": 288,
370
+ "ai": 289,
371
+ "el": 290,
372
+ "er": 291,
373
+ "jou": 292,
374
+ "on": 293,
375
+ "re": 294,
376
+ "Quel": 295,
377
+ "eux": 296,
378
+ "Ġest": 297,
379
+ "Chu": 298,
380
+ "Sa": 299,
381
+ "cou": 300,
382
+ "la": 301,
383
+ "lu": 302,
384
+ "qu": 303,
385
+ "ré": 304,
386
+ "ç": 305,
387
+ "Ġb": 306,
388
+ "ĠPika": 307,
389
+ "Ġas": 308,
390
+ "Ġqu": 309,
391
+ "Ġ!!": 310,
392
+ "Ġvas": 311,
393
+ "Ġfai": 312,
394
+ "Ġton": 313,
395
+ "jour": 314,
396
+ "lut": 315,
397
+ "Ġquoi": 316
398
+ },
399
+ "merges": [
400
+ [
401
+ "i",
402
+ "k"
403
+ ],
404
+ [
405
+ "ik",
406
+ "a"
407
+ ],
408
+ [
409
+ "P",
410
+ "ika"
411
+ ],
412
+ [
413
+ "Ġ",
414
+ "?"
415
+ ],
416
+ [
417
+ ".",
418
+ "."
419
+ ],
420
+ [
421
+ "h",
422
+ "u"
423
+ ],
424
+ [
425
+ "Ġ",
426
+ "p"
427
+ ],
428
+ [
429
+ "c",
430
+ "hu"
431
+ ],
432
+ [
433
+ "Ġ",
434
+ "!"
435
+ ],
436
+ [
437
+ "Ġp",
438
+ "ika"
439
+ ],
440
+ [
441
+ "e",
442
+ "s"
443
+ ],
444
+ [
445
+ "T",
446
+ "u"
447
+ ],
448
+ [
449
+ "o",
450
+ "u"
451
+ ],
452
+ [
453
+ "..",
454
+ "."
455
+ ],
456
+ [
457
+ "Q",
458
+ "u"
459
+ ],
460
+ [
461
+ "e",
462
+ "u"
463
+ ],
464
+ [
465
+ "Ġ",
466
+ "v"
467
+ ],
468
+ [
469
+ "Ġ",
470
+ "chu"
471
+ ],
472
+ [
473
+ "Ġ",
474
+ "es"
475
+ ],
476
+ [
477
+ "Pika",
478
+ "chu"
479
+ ],
480
+ [
481
+ "a",
482
+ "s"
483
+ ],
484
+ [
485
+ "e",
486
+ "n"
487
+ ],
488
+ [
489
+ "o",
490
+ "i"
491
+ ],
492
+ [
493
+ "p",
494
+ "ika"
495
+ ],
496
+ [
497
+ "t",
498
+ "u"
499
+ ],
500
+ [
501
+ "Ã",
502
+ "©"
503
+ ],
504
+ [
505
+ "Ġ",
506
+ "f"
507
+ ],
508
+ [
509
+ "Ġ",
510
+ "t"
511
+ ],
512
+ [
513
+ "a",
514
+ "i"
515
+ ],
516
+ [
517
+ "e",
518
+ "l"
519
+ ],
520
+ [
521
+ "e",
522
+ "r"
523
+ ],
524
+ [
525
+ "j",
526
+ "ou"
527
+ ],
528
+ [
529
+ "o",
530
+ "n"
531
+ ],
532
+ [
533
+ "r",
534
+ "e"
535
+ ],
536
+ [
537
+ "Qu",
538
+ "el"
539
+ ],
540
+ [
541
+ "eu",
542
+ "x"
543
+ ],
544
+ [
545
+ "Ġes",
546
+ "t"
547
+ ],
548
+ [
549
+ "C",
550
+ "hu"
551
+ ],
552
+ [
553
+ "S",
554
+ "a"
555
+ ],
556
+ [
557
+ "c",
558
+ "ou"
559
+ ],
560
+ [
561
+ "l",
562
+ "a"
563
+ ],
564
+ [
565
+ "l",
566
+ "u"
567
+ ],
568
+ [
569
+ "q",
570
+ "u"
571
+ ],
572
+ [
573
+ "r",
574
+ "é"
575
+ ],
576
+ [
577
+ "Ã",
578
+ "§"
579
+ ],
580
+ [
581
+ "Ġ",
582
+ "b"
583
+ ],
584
+ [
585
+ "Ġ",
586
+ "Pika"
587
+ ],
588
+ [
589
+ "Ġ",
590
+ "as"
591
+ ],
592
+ [
593
+ "Ġ",
594
+ "qu"
595
+ ],
596
+ [
597
+ "Ġ!",
598
+ "!"
599
+ ],
600
+ [
601
+ "Ġv",
602
+ "as"
603
+ ],
604
+ [
605
+ "Ġf",
606
+ "ai"
607
+ ],
608
+ [
609
+ "Ġt",
610
+ "on"
611
+ ],
612
+ [
613
+ "jou",
614
+ "r"
615
+ ],
616
+ [
617
+ "lu",
618
+ "t"
619
+ ],
620
+ [
621
+ "Ġqu",
622
+ "oi"
623
+ ]
624
+ ]
625
+ }
626
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "</s>",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "unk_token": "<unk>"
53
+ }