kichan05 commited on
Commit
bc4cdf2
1 Parent(s): b80a56c

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +50 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +51 -23
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +392 -27
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 50256,
3
+ "<||bos||>": 50257,
4
+ "<||pad||>": 50258,
5
+ "<||unk||>": 50259,
6
+ "<||unused10||>": 50269,
7
+ "<||unused11||>": 50270,
8
+ "<||unused12||>": 50271,
9
+ "<||unused13||>": 50272,
10
+ "<||unused14||>": 50273,
11
+ "<||unused15||>": 50274,
12
+ "<||unused16||>": 50275,
13
+ "<||unused17||>": 50276,
14
+ "<||unused18||>": 50277,
15
+ "<||unused19||>": 50278,
16
+ "<||unused1||>": 50260,
17
+ "<||unused20||>": 50279,
18
+ "<||unused21||>": 50280,
19
+ "<||unused22||>": 50281,
20
+ "<||unused23||>": 50282,
21
+ "<||unused24||>": 50283,
22
+ "<||unused25||>": 50284,
23
+ "<||unused26||>": 50285,
24
+ "<||unused27||>": 50286,
25
+ "<||unused28||>": 50287,
26
+ "<||unused29||>": 50288,
27
+ "<||unused2||>": 50261,
28
+ "<||unused30||>": 50289,
29
+ "<||unused31||>": 50290,
30
+ "<||unused32||>": 50291,
31
+ "<||unused33||>": 50292,
32
+ "<||unused34||>": 50293,
33
+ "<||unused35||>": 50294,
34
+ "<||unused36||>": 50295,
35
+ "<||unused37||>": 50296,
36
+ "<||unused38||>": 50297,
37
+ "<||unused39||>": 50298,
38
+ "<||unused3||>": 50262,
39
+ "<||unused40||>": 50299,
40
+ "<||unused41||>": 50300,
41
+ "<||unused42||>": 50301,
42
+ "<||unused43||>": 50302,
43
+ "<||unused44||>": 50303,
44
+ "<||unused4||>": 50263,
45
+ "<||unused5||>": 50264,
46
+ "<||unused6||>": 50265,
47
+ "<||unused7||>": 50266,
48
+ "<||unused8||>": 50267,
49
+ "<||unused9||>": 50268
50
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,30 +1,58 @@
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": "</s>",
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
  }
 
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|>",
51
  "lstrip": false,
52
+ "normalized": true,
53
  "rstrip": false,
54
  "single_word": false
55
  },
56
+ "pad_token": "<||pad||>",
57
+ "unk_token": "<||unk||>"
 
 
 
 
 
 
 
 
 
 
 
 
58
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,65 +1,385 @@
1
  {
2
  "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
 
 
 
 
 
 
 
 
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1": {
14
- "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
- "46331": {
30
- "content": "<|sep|>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
- "46332": {
38
- "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  },
45
- "46333": {
46
- "content": "<|acc|>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
  "special": true
52
  },
53
- "46334": {
54
- "content": "<|rrn|>",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
  "special": true
60
  },
61
- "46335": {
62
- "content": "<|tel|>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": false,
@@ -67,14 +387,59 @@
67
  "special": true
68
  }
69
  },
70
- "bos_token": "<s>",
71
- "clean_up_tokenization_spaces": false,
72
- "eos_token": "</s>",
73
- "legacy": false,
74
- "model_max_length": 1000000000000000019884624838656,
75
- "pad_token": "</s>",
76
- "sp_model_kwargs": {},
77
- "tokenizer_class": "LlamaTokenizer",
78
- "unk_token": "<unk>",
79
- "use_default_system_prompt": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  }
 
1
  {
2
  "add_bos_token": true,
3
+ "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<||bos||>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "50258": {
22
+ "content": "<||pad||>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "50259": {
30
+ "content": "<||unk||>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "50260": {
38
+ "content": "<||unused1||>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  },
45
+ "50261": {
46
+ "content": "<||unused2||>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<||unused3||>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50263": {
62
+ "content": "<||unused4||>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50264": {
70
+ "content": "<||unused5||>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50265": {
78
+ "content": "<||unused6||>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50266": {
86
+ "content": "<||unused7||>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50267": {
94
+ "content": "<||unused8||>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "50268": {
102
+ "content": "<||unused9||>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "50269": {
110
+ "content": "<||unused10||>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "50270": {
118
+ "content": "<||unused11||>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "50271": {
126
+ "content": "<||unused12||>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "50272": {
134
+ "content": "<||unused13||>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "50273": {
142
+ "content": "<||unused14||>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "50274": {
150
+ "content": "<||unused15||>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "50275": {
158
+ "content": "<||unused16||>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "50276": {
166
+ "content": "<||unused17||>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "50277": {
174
+ "content": "<||unused18||>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "50278": {
182
+ "content": "<||unused19||>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "50279": {
190
+ "content": "<||unused20||>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "50280": {
198
+ "content": "<||unused21||>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "50281": {
206
+ "content": "<||unused22||>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "50282": {
214
+ "content": "<||unused23||>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "50283": {
222
+ "content": "<||unused24||>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "50284": {
230
+ "content": "<||unused25||>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "50285": {
238
+ "content": "<||unused26||>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "50286": {
246
+ "content": "<||unused27||>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "50287": {
254
+ "content": "<||unused28||>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "50288": {
262
+ "content": "<||unused29||>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "50289": {
270
+ "content": "<||unused30||>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "50290": {
278
+ "content": "<||unused31||>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "50291": {
286
+ "content": "<||unused32||>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "50292": {
294
+ "content": "<||unused33||>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "50293": {
302
+ "content": "<||unused34||>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "50294": {
310
+ "content": "<||unused35||>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "50295": {
318
+ "content": "<||unused36||>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "50296": {
326
+ "content": "<||unused37||>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "50297": {
334
+ "content": "<||unused38||>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "50298": {
342
+ "content": "<||unused39||>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "50299": {
350
+ "content": "<||unused40||>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "50300": {
358
+ "content": "<||unused41||>",
359
  "lstrip": false,
360
  "normalized": false,
361
  "rstrip": false,
362
  "single_word": false,
363
  "special": true
364
  },
365
+ "50301": {
366
+ "content": "<||unused42||>",
367
  "lstrip": false,
368
  "normalized": false,
369
  "rstrip": false,
370
  "single_word": false,
371
  "special": true
372
  },
373
+ "50302": {
374
+ "content": "<||unused43||>",
375
  "lstrip": false,
376
  "normalized": false,
377
  "rstrip": false,
378
  "single_word": false,
379
  "special": true
380
  },
381
+ "50303": {
382
+ "content": "<||unused44||>",
383
  "lstrip": false,
384
  "normalized": false,
385
  "rstrip": false,
 
387
  "special": true
388
  }
389
  },
390
+ "additional_special_tokens": [
391
+ "<||unused1||>",
392
+ "<||unused2||>",
393
+ "<||unused3||>",
394
+ "<||unused4||>",
395
+ "<||unused5||>",
396
+ "<||unused6||>",
397
+ "<||unused7||>",
398
+ "<||unused8||>",
399
+ "<||unused9||>",
400
+ "<||unused10||>",
401
+ "<||unused11||>",
402
+ "<||unused12||>",
403
+ "<||unused13||>",
404
+ "<||unused14||>",
405
+ "<||unused15||>",
406
+ "<||unused16||>",
407
+ "<||unused17||>",
408
+ "<||unused18||>",
409
+ "<||unused19||>",
410
+ "<||unused20||>",
411
+ "<||unused21||>",
412
+ "<||unused22||>",
413
+ "<||unused23||>",
414
+ "<||unused24||>",
415
+ "<||unused25||>",
416
+ "<||unused26||>",
417
+ "<||unused27||>",
418
+ "<||unused28||>",
419
+ "<||unused29||>",
420
+ "<||unused30||>",
421
+ "<||unused31||>",
422
+ "<||unused32||>",
423
+ "<||unused33||>",
424
+ "<||unused34||>",
425
+ "<||unused35||>",
426
+ "<||unused36||>",
427
+ "<||unused37||>",
428
+ "<||unused38||>",
429
+ "<||unused39||>",
430
+ "<||unused40||>",
431
+ "<||unused41||>",
432
+ "<||unused42||>",
433
+ "<||unused43||>",
434
+ "<||unused44||>"
435
+ ],
436
+ "bos_token": "<||bos||>",
437
+ "clean_up_tokenization_spaces": true,
438
+ "eos_token": "<|endoftext|>",
439
+ "errors": "replace",
440
+ "model_max_length": 8192,
441
+ "pad_token": "<||pad||>",
442
+ "padding_side": "right",
443
+ "tokenizer_class": "GPT2Tokenizer",
444
+ "unk_token": "<||unk||>"
445
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff