WICKED4950 commited on
Commit
9460f42
·
verified ·
1 Parent(s): 5ecea1c

Upload tokenizer/yap.json with huggingface_hub

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