gigant commited on
Commit
f2caa95
·
verified ·
1 Parent(s): d54adc4

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +330 -0
tokenizer.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<pad>",
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
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "ByteLevel",
46
+ "add_prefix_space": false,
47
+ "trim_offsets": true,
48
+ "use_regex": true
49
+ },
50
+ "post_processor": null,
51
+ "decoder": {
52
+ "type": "ByteLevel",
53
+ "add_prefix_space": true,
54
+ "trim_offsets": true,
55
+ "use_regex": true
56
+ },
57
+ "model": {
58
+ "type": "BPE",
59
+ "dropout": null,
60
+ "unk_token": null,
61
+ "continuing_subword_prefix": null,
62
+ "end_of_word_suffix": null,
63
+ "fuse_unk": false,
64
+ "byte_fallback": false,
65
+ "ignore_merges": false,
66
+ "vocab": {
67
+ "<s>": 0,
68
+ "</s>": 1,
69
+ "<pad>": 2,
70
+ "<unk>": 3,
71
+ "!": 4,
72
+ "\"": 5,
73
+ "#": 6,
74
+ "$": 7,
75
+ "%": 8,
76
+ "&": 9,
77
+ "'": 10,
78
+ "(": 11,
79
+ ")": 12,
80
+ "*": 13,
81
+ "+": 14,
82
+ ",": 15,
83
+ "-": 16,
84
+ ".": 17,
85
+ "/": 18,
86
+ "0": 19,
87
+ "1": 20,
88
+ "2": 21,
89
+ "3": 22,
90
+ "4": 23,
91
+ "5": 24,
92
+ "6": 25,
93
+ "7": 26,
94
+ "8": 27,
95
+ "9": 28,
96
+ ":": 29,
97
+ ";": 30,
98
+ "<": 31,
99
+ "=": 32,
100
+ ">": 33,
101
+ "?": 34,
102
+ "@": 35,
103
+ "A": 36,
104
+ "B": 37,
105
+ "C": 38,
106
+ "D": 39,
107
+ "E": 40,
108
+ "F": 41,
109
+ "G": 42,
110
+ "H": 43,
111
+ "I": 44,
112
+ "J": 45,
113
+ "K": 46,
114
+ "L": 47,
115
+ "M": 48,
116
+ "N": 49,
117
+ "O": 50,
118
+ "P": 51,
119
+ "Q": 52,
120
+ "R": 53,
121
+ "S": 54,
122
+ "T": 55,
123
+ "U": 56,
124
+ "V": 57,
125
+ "W": 58,
126
+ "X": 59,
127
+ "Y": 60,
128
+ "Z": 61,
129
+ "[": 62,
130
+ "\\": 63,
131
+ "]": 64,
132
+ "^": 65,
133
+ "_": 66,
134
+ "`": 67,
135
+ "a": 68,
136
+ "b": 69,
137
+ "c": 70,
138
+ "d": 71,
139
+ "e": 72,
140
+ "f": 73,
141
+ "g": 74,
142
+ "h": 75,
143
+ "i": 76,
144
+ "j": 77,
145
+ "k": 78,
146
+ "l": 79,
147
+ "m": 80,
148
+ "n": 81,
149
+ "o": 82,
150
+ "p": 83,
151
+ "q": 84,
152
+ "r": 85,
153
+ "s": 86,
154
+ "t": 87,
155
+ "u": 88,
156
+ "v": 89,
157
+ "w": 90,
158
+ "x": 91,
159
+ "y": 92,
160
+ "z": 93,
161
+ "{": 94,
162
+ "|": 95,
163
+ "}": 96,
164
+ "~": 97,
165
+ "¡": 98,
166
+ "¢": 99,
167
+ "£": 100,
168
+ "¤": 101,
169
+ "¥": 102,
170
+ "¦": 103,
171
+ "§": 104,
172
+ "¨": 105,
173
+ "©": 106,
174
+ "ª": 107,
175
+ "«": 108,
176
+ "¬": 109,
177
+ "®": 110,
178
+ "¯": 111,
179
+ "°": 112,
180
+ "±": 113,
181
+ "²": 114,
182
+ "³": 115,
183
+ "´": 116,
184
+ "µ": 117,
185
+ "¶": 118,
186
+ "·": 119,
187
+ "¸": 120,
188
+ "¹": 121,
189
+ "º": 122,
190
+ "»": 123,
191
+ "¼": 124,
192
+ "½": 125,
193
+ "¾": 126,
194
+ "¿": 127,
195
+ "À": 128,
196
+ "Á": 129,
197
+ "Â": 130,
198
+ "Ã": 131,
199
+ "Ä": 132,
200
+ "Å": 133,
201
+ "Æ": 134,
202
+ "Ç": 135,
203
+ "È": 136,
204
+ "É": 137,
205
+ "Ê": 138,
206
+ "Ë": 139,
207
+ "Ì": 140,
208
+ "Í": 141,
209
+ "Î": 142,
210
+ "Ï": 143,
211
+ "Ð": 144,
212
+ "Ñ": 145,
213
+ "Ò": 146,
214
+ "Ó": 147,
215
+ "Ô": 148,
216
+ "Õ": 149,
217
+ "Ö": 150,
218
+ "×": 151,
219
+ "Ø": 152,
220
+ "Ù": 153,
221
+ "Ú": 154,
222
+ "Û": 155,
223
+ "Ü": 156,
224
+ "Ý": 157,
225
+ "Þ": 158,
226
+ "ß": 159,
227
+ "à": 160,
228
+ "á": 161,
229
+ "â": 162,
230
+ "ã": 163,
231
+ "ä": 164,
232
+ "å": 165,
233
+ "æ": 166,
234
+ "ç": 167,
235
+ "è": 168,
236
+ "é": 169,
237
+ "ê": 170,
238
+ "ë": 171,
239
+ "ì": 172,
240
+ "í": 173,
241
+ "î": 174,
242
+ "ï": 175,
243
+ "ð": 176,
244
+ "ñ": 177,
245
+ "ò": 178,
246
+ "ó": 179,
247
+ "ô": 180,
248
+ "õ": 181,
249
+ "ö": 182,
250
+ "÷": 183,
251
+ "ø": 184,
252
+ "ù": 185,
253
+ "ú": 186,
254
+ "û": 187,
255
+ "ü": 188,
256
+ "ý": 189,
257
+ "þ": 190,
258
+ "ÿ": 191,
259
+ "Ā": 192,
260
+ "ā": 193,
261
+ "Ă": 194,
262
+ "ă": 195,
263
+ "Ą": 196,
264
+ "ą": 197,
265
+ "Ć": 198,
266
+ "ć": 199,
267
+ "Ĉ": 200,
268
+ "ĉ": 201,
269
+ "Ċ": 202,
270
+ "ċ": 203,
271
+ "Č": 204,
272
+ "č": 205,
273
+ "Ď": 206,
274
+ "ď": 207,
275
+ "Đ": 208,
276
+ "đ": 209,
277
+ "Ē": 210,
278
+ "ē": 211,
279
+ "Ĕ": 212,
280
+ "ĕ": 213,
281
+ "Ė": 214,
282
+ "ė": 215,
283
+ "Ę": 216,
284
+ "ę": 217,
285
+ "Ě": 218,
286
+ "ě": 219,
287
+ "Ĝ": 220,
288
+ "ĝ": 221,
289
+ "Ğ": 222,
290
+ "ğ": 223,
291
+ "Ġ": 224,
292
+ "ġ": 225,
293
+ "Ģ": 226,
294
+ "ģ": 227,
295
+ "Ĥ": 228,
296
+ "ĥ": 229,
297
+ "Ħ": 230,
298
+ "ħ": 231,
299
+ "Ĩ": 232,
300
+ "ĩ": 233,
301
+ "Ī": 234,
302
+ "ī": 235,
303
+ "Ĭ": 236,
304
+ "ĭ": 237,
305
+ "Į": 238,
306
+ "į": 239,
307
+ "İ": 240,
308
+ "ı": 241,
309
+ "IJ": 242,
310
+ "ij": 243,
311
+ "Ĵ": 244,
312
+ "ĵ": 245,
313
+ "Ķ": 246,
314
+ "ķ": 247,
315
+ "ĸ": 248,
316
+ "Ĺ": 249,
317
+ "ĺ": 250,
318
+ "Ļ": 251,
319
+ "ļ": 252,
320
+ "Ľ": 253,
321
+ "ľ": 254,
322
+ "Ŀ": 255,
323
+ "ŀ": 256,
324
+ "Ł": 257,
325
+ "ł": 258,
326
+ "Ń": 259
327
+ },
328
+ "merges": []
329
+ }
330
+ }