Hugging Face's logo

InfoTokenizers
/
tokenizers

Model card Files Community
pietrolesci commited on
Commit
592b2b4
·
verified ·
1 Parent(s): 6e279d2

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. bytelevel/special_tokens_map.json +4 -0
  2. bytelevel/tokenizer.json +322 -0
  3. bytelevel/tokenizer_config.json +29 -0
bytelevel/special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|padding|>"
4
+ }
bytelevel/tokenizer.json ADDED
@@ -0,0 +1,322 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|padding|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": {
26
+ "type": "Sequence",
27
+ "normalizers": [
28
+ {
29
+ "type": "NFD"
30
+ }
31
+ ]
32
+ },
33
+ "pre_tokenizer": {
34
+ "type": "ByteLevel",
35
+ "add_prefix_space": true,
36
+ "trim_offsets": true,
37
+ "use_regex": true
38
+ },
39
+ "post_processor": {
40
+ "type": "ByteLevel",
41
+ "add_prefix_space": true,
42
+ "trim_offsets": true,
43
+ "use_regex": true
44
+ },
45
+ "decoder": {
46
+ "type": "ByteLevel",
47
+ "add_prefix_space": true,
48
+ "trim_offsets": true,
49
+ "use_regex": true
50
+ },
51
+ "model": {
52
+ "type": "BPE",
53
+ "dropout": null,
54
+ "unk_token": null,
55
+ "continuing_subword_prefix": null,
56
+ "end_of_word_suffix": null,
57
+ "fuse_unk": false,
58
+ "byte_fallback": false,
59
+ "ignore_merges": false,
60
+ "vocab": {
61
+ "<|padding|>": 0,
62
+ "<|endoftext|>": 1,
63
+ "!": 2,
64
+ "\"": 3,
65
+ "#": 4,
66
+ "$": 5,
67
+ "%": 6,
68
+ "&": 7,
69
+ "'": 8,
70
+ "(": 9,
71
+ ")": 10,
72
+ "*": 11,
73
+ "+": 12,
74
+ ",": 13,
75
+ "-": 14,
76
+ ".": 15,
77
+ "/": 16,
78
+ "0": 17,
79
+ "1": 18,
80
+ "2": 19,
81
+ "3": 20,
82
+ "4": 21,
83
+ "5": 22,
84
+ "6": 23,
85
+ "7": 24,
86
+ "8": 25,
87
+ "9": 26,
88
+ ":": 27,
89
+ ";": 28,
90
+ "<": 29,
91
+ "=": 30,
92
+ ">": 31,
93
+ "?": 32,
94
+ "@": 33,
95
+ "A": 34,
96
+ "B": 35,
97
+ "C": 36,
98
+ "D": 37,
99
+ "E": 38,
100
+ "F": 39,
101
+ "G": 40,
102
+ "H": 41,
103
+ "I": 42,
104
+ "J": 43,
105
+ "K": 44,
106
+ "L": 45,
107
+ "M": 46,
108
+ "N": 47,
109
+ "O": 48,
110
+ "P": 49,
111
+ "Q": 50,
112
+ "R": 51,
113
+ "S": 52,
114
+ "T": 53,
115
+ "U": 54,
116
+ "V": 55,
117
+ "W": 56,
118
+ "X": 57,
119
+ "Y": 58,
120
+ "Z": 59,
121
+ "[": 60,
122
+ "\\": 61,
123
+ "]": 62,
124
+ "^": 63,
125
+ "_": 64,
126
+ "`": 65,
127
+ "a": 66,
128
+ "b": 67,
129
+ "c": 68,
130
+ "d": 69,
131
+ "e": 70,
132
+ "f": 71,
133
+ "g": 72,
134
+ "h": 73,
135
+ "i": 74,
136
+ "j": 75,
137
+ "k": 76,
138
+ "l": 77,
139
+ "m": 78,
140
+ "n": 79,
141
+ "o": 80,
142
+ "p": 81,
143
+ "q": 82,
144
+ "r": 83,
145
+ "s": 84,
146
+ "t": 85,
147
+ "u": 86,
148
+ "v": 87,
149
+ "w": 88,
150
+ "x": 89,
151
+ "y": 90,
152
+ "z": 91,
153
+ "{": 92,
154
+ "|": 93,
155
+ "}": 94,
156
+ "~": 95,
157
+ "¡": 96,
158
+ "¢": 97,
159
+ "£": 98,
160
+ "¤": 99,
161
+ "¥": 100,
162
+ "¦": 101,
163
+ "§": 102,
164
+ "¨": 103,
165
+ "©": 104,
166
+ "ª": 105,
167
+ "«": 106,
168
+ "¬": 107,
169
+ "®": 108,
170
+ "¯": 109,
171
+ "°": 110,
172
+ "±": 111,
173
+ "²": 112,
174
+ "³": 113,
175
+ "´": 114,
176
+ "µ": 115,
177
+ "¶": 116,
178
+ "·": 117,
179
+ "¸": 118,
180
+ "¹": 119,
181
+ "º": 120,
182
+ "»": 121,
183
+ "¼": 122,
184
+ "½": 123,
185
+ "¾": 124,
186
+ "¿": 125,
187
+ "À": 126,
188
+ "Á": 127,
189
+ "Â": 128,
190
+ "Ã": 129,
191
+ "Ä": 130,
192
+ "Å": 131,
193
+ "Æ": 132,
194
+ "Ç": 133,
195
+ "È": 134,
196
+ "É": 135,
197
+ "Ê": 136,
198
+ "Ë": 137,
199
+ "Ì": 138,
200
+ "Í": 139,
201
+ "Î": 140,
202
+ "Ï": 141,
203
+ "Ð": 142,
204
+ "Ñ": 143,
205
+ "Ò": 144,
206
+ "Ó": 145,
207
+ "Ô": 146,
208
+ "Õ": 147,
209
+ "Ö": 148,
210
+ "×": 149,
211
+ "Ø": 150,
212
+ "Ù": 151,
213
+ "Ú": 152,
214
+ "Û": 153,
215
+ "Ü": 154,
216
+ "Ý": 155,
217
+ "Þ": 156,
218
+ "ß": 157,
219
+ "à": 158,
220
+ "á": 159,
221
+ "â": 160,
222
+ "ã": 161,
223
+ "ä": 162,
224
+ "å": 163,
225
+ "æ": 164,
226
+ "ç": 165,
227
+ "è": 166,
228
+ "é": 167,
229
+ "ê": 168,
230
+ "ë": 169,
231
+ "ì": 170,
232
+ "í": 171,
233
+ "î": 172,
234
+ "ï": 173,
235
+ "ð": 174,
236
+ "ñ": 175,
237
+ "ò": 176,
238
+ "ó": 177,
239
+ "ô": 178,
240
+ "õ": 179,
241
+ "ö": 180,
242
+ "÷": 181,
243
+ "ø": 182,
244
+ "ù": 183,
245
+ "ú": 184,
246
+ "û": 185,
247
+ "ü": 186,
248
+ "ý": 187,
249
+ "þ": 188,
250
+ "ÿ": 189,
251
+ "Ā": 190,
252
+ "ā": 191,
253
+ "Ă": 192,
254
+ "ă": 193,
255
+ "Ą": 194,
256
+ "ą": 195,
257
+ "Ć": 196,
258
+ "ć": 197,
259
+ "Ĉ": 198,
260
+ "ĉ": 199,
261
+ "Ċ": 200,
262
+ "ċ": 201,
263
+ "Č": 202,
264
+ "č": 203,
265
+ "Ď": 204,
266
+ "ď": 205,
267
+ "Đ": 206,
268
+ "đ": 207,
269
+ "Ē": 208,
270
+ "ē": 209,
271
+ "Ĕ": 210,
272
+ "ĕ": 211,
273
+ "Ė": 212,
274
+ "ė": 213,
275
+ "Ę": 214,
276
+ "ę": 215,
277
+ "Ě": 216,
278
+ "ě": 217,
279
+ "Ĝ": 218,
280
+ "ĝ": 219,
281
+ "Ğ": 220,
282
+ "ğ": 221,
283
+ "Ġ": 222,
284
+ "ġ": 223,
285
+ "Ģ": 224,
286
+ "ģ": 225,
287
+ "Ĥ": 226,
288
+ "ĥ": 227,
289
+ "Ħ": 228,
290
+ "ħ": 229,
291
+ "Ĩ": 230,
292
+ "ĩ": 231,
293
+ "Ī": 232,
294
+ "ī": 233,
295
+ "Ĭ": 234,
296
+ "ĭ": 235,
297
+ "Į": 236,
298
+ "į": 237,
299
+ "İ": 238,
300
+ "ı": 239,
301
+ "IJ": 240,
302
+ "ij": 241,
303
+ "Ĵ": 242,
304
+ "ĵ": 243,
305
+ "Ķ": 244,
306
+ "ķ": 245,
307
+ "ĸ": 246,
308
+ "Ĺ": 247,
309
+ "ĺ": 248,
310
+ "Ļ": 249,
311
+ "ļ": 250,
312
+ "Ľ": 251,
313
+ "ľ": 252,
314
+ "Ŀ": 253,
315
+ "ŀ": 254,
316
+ "Ł": 255,
317
+ "ł": 256,
318
+ "Ń": 257
319
+ },
320
+ "merges": []
321
+ }
322
+ }
bytelevel/tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|padding|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": null,
22
+ "clean_up_tokenization_spaces": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "extra_special_tokens": {},
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "pad_token": "<|padding|>",
27
+ "tokenizer_class": "PreTrainedTokenizer",
28
+ "unk_token": null
29
+ }