yongtae-jp commited on
Commit
0ffac1b
1 Parent(s): 4681dac

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32056,
3
+ "<|extra_0|>": 32000,
4
+ "<|extra_10|>": 32010,
5
+ "<|extra_11|>": 32011,
6
+ "<|extra_12|>": 32012,
7
+ "<|extra_13|>": 32013,
8
+ "<|extra_14|>": 32014,
9
+ "<|extra_15|>": 32015,
10
+ "<|extra_16|>": 32016,
11
+ "<|extra_17|>": 32017,
12
+ "<|extra_18|>": 32018,
13
+ "<|extra_19|>": 32019,
14
+ "<|extra_1|>": 32001,
15
+ "<|extra_20|>": 32020,
16
+ "<|extra_21|>": 32021,
17
+ "<|extra_22|>": 32022,
18
+ "<|extra_23|>": 32023,
19
+ "<|extra_24|>": 32024,
20
+ "<|extra_25|>": 32025,
21
+ "<|extra_26|>": 32026,
22
+ "<|extra_27|>": 32027,
23
+ "<|extra_28|>": 32028,
24
+ "<|extra_29|>": 32029,
25
+ "<|extra_2|>": 32002,
26
+ "<|extra_30|>": 32030,
27
+ "<|extra_31|>": 32031,
28
+ "<|extra_32|>": 32032,
29
+ "<|extra_33|>": 32033,
30
+ "<|extra_34|>": 32034,
31
+ "<|extra_35|>": 32035,
32
+ "<|extra_36|>": 32036,
33
+ "<|extra_37|>": 32037,
34
+ "<|extra_38|>": 32038,
35
+ "<|extra_39|>": 32039,
36
+ "<|extra_3|>": 32003,
37
+ "<|extra_40|>": 32040,
38
+ "<|extra_41|>": 32041,
39
+ "<|extra_42|>": 32042,
40
+ "<|extra_43|>": 32043,
41
+ "<|extra_44|>": 32044,
42
+ "<|extra_45|>": 32045,
43
+ "<|extra_46|>": 32046,
44
+ "<|extra_47|>": 32047,
45
+ "<|extra_48|>": 32048,
46
+ "<|extra_49|>": 32049,
47
+ "<|extra_4|>": 32004,
48
+ "<|extra_50|>": 32050,
49
+ "<|extra_51|>": 32051,
50
+ "<|extra_52|>": 32052,
51
+ "<|extra_53|>": 32053,
52
+ "<|extra_54|>": 32054,
53
+ "<|extra_5|>": 32005,
54
+ "<|extra_6|>": 32006,
55
+ "<|extra_7|>": 32007,
56
+ "<|extra_8|>": 32008,
57
+ "<|extra_9|>": 32009,
58
+ "<|pad_0|>": 32055
59
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,500 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
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
+ "32000": {
28
+ "content": "<|extra_0|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "32001": {
36
+ "content": "<|extra_1|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "32002": {
44
+ "content": "<|extra_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "32003": {
52
+ "content": "<|extra_3|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "32004": {
60
+ "content": "<|extra_4|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "32005": {
68
+ "content": "<|extra_5|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "32006": {
76
+ "content": "<|extra_6|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "32007": {
84
+ "content": "<|extra_7|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "32008": {
92
+ "content": "<|extra_8|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "32009": {
100
+ "content": "<|extra_9|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "32010": {
108
+ "content": "<|extra_10|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "32011": {
116
+ "content": "<|extra_11|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "32012": {
124
+ "content": "<|extra_12|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "32013": {
132
+ "content": "<|extra_13|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "32014": {
140
+ "content": "<|extra_14|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "32015": {
148
+ "content": "<|extra_15|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "32016": {
156
+ "content": "<|extra_16|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "32017": {
164
+ "content": "<|extra_17|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "32018": {
172
+ "content": "<|extra_18|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "32019": {
180
+ "content": "<|extra_19|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "32020": {
188
+ "content": "<|extra_20|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "32021": {
196
+ "content": "<|extra_21|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "32022": {
204
+ "content": "<|extra_22|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "32023": {
212
+ "content": "<|extra_23|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "32024": {
220
+ "content": "<|extra_24|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "32025": {
228
+ "content": "<|extra_25|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "32026": {
236
+ "content": "<|extra_26|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "32027": {
244
+ "content": "<|extra_27|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "32028": {
252
+ "content": "<|extra_28|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "32029": {
260
+ "content": "<|extra_29|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "32030": {
268
+ "content": "<|extra_30|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "32031": {
276
+ "content": "<|extra_31|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "32032": {
284
+ "content": "<|extra_32|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "32033": {
292
+ "content": "<|extra_33|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "32034": {
300
+ "content": "<|extra_34|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "32035": {
308
+ "content": "<|extra_35|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "32036": {
316
+ "content": "<|extra_36|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "32037": {
324
+ "content": "<|extra_37|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "32038": {
332
+ "content": "<|extra_38|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "32039": {
340
+ "content": "<|extra_39|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "32040": {
348
+ "content": "<|extra_40|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "32041": {
356
+ "content": "<|extra_41|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "32042": {
364
+ "content": "<|extra_42|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "32043": {
372
+ "content": "<|extra_43|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "32044": {
380
+ "content": "<|extra_44|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "32045": {
388
+ "content": "<|extra_45|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "32046": {
396
+ "content": "<|extra_46|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "32047": {
404
+ "content": "<|extra_47|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "32048": {
412
+ "content": "<|extra_48|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "32049": {
420
+ "content": "<|extra_49|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "32050": {
428
+ "content": "<|extra_50|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "32051": {
436
+ "content": "<|extra_51|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "32052": {
444
+ "content": "<|extra_52|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "32053": {
452
+ "content": "<|extra_53|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "32054": {
460
+ "content": "<|extra_54|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "32055": {
468
+ "content": "<|pad_0|>",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "32056": {
476
+ "content": "<|end_of_turn|>",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ }
483
+ },
484
+ "additional_special_tokens": [],
485
+ "bos_token": "<s>",
486
+ "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- bos_token + '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}\n",
487
+ "clean_up_tokenization_spaces": false,
488
+ "eos_token": "</s>",
489
+ "legacy": true,
490
+ "model_max_length": 1000000000000000019884624838656,
491
+ "pad_token": "<unk>",
492
+ "padding_side": "right",
493
+ "sp_model_kwargs": {},
494
+ "spaces_between_special_tokens": false,
495
+ "tokenizer_class": "LlamaTokenizer",
496
+ "trust_remote_code": false,
497
+ "unk_token": "<unk>",
498
+ "use_default_system_prompt": false,
499
+ "use_fast": true
500
+ }