Xenova HF staff commited on
Commit
73d7339
·
verified ·
1 Parent(s): 4685882

Update tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +12 -74
tokenizer.json CHANGED
@@ -6,7 +6,7 @@
6
  "normalizer": {
7
  "type": "Replace",
8
  "pattern": {
9
- "Regex": "[^ !\"$',.:;?A-Za-z\u00a1\u00ab\u00bb\u00bf\u00e6\u00e7\u00f0\u00f8\u0127\u014b\u0153\u01c0-\u01c3\u0250-\u0268\u026a-\u0276\u0278-\u027b\u027d\u027e\u0280-\u0284\u0288-\u0292\u0294\u0295\u0298\u0299\u029b-\u029d\u029f\u02a1\u02a2\u02a4\u02a7\u02b0-\u02b2\u02b4\u02b7\u02bc\u02c8\u02cc\u02d0\u02d1\u02de\u02e0\u02e4\u0329\u03b2\u03b8\u03c7\u1d7b\u2014\u201c\u201d\u2026\u2191-\u2193\u2197\u2198\u2c71]"
10
  },
11
  "content": ""
12
  },
@@ -62,49 +62,36 @@
62
  ".": 4,
63
  "!": 5,
64
  "?": 6,
65
- "\u00a1": 7,
66
- "\u00bf": 8,
67
  "\u2014": 9,
68
  "\u2026": 10,
69
  "\"": 11,
70
- "\u00ab": 12,
71
- "\u00bb": 13,
72
  "\u201c": 14,
73
  "\u201d": 15,
74
  " ": 16,
75
- "A": 17,
76
- "B": 18,
77
- "C": 19,
78
- "D": 20,
79
- "E": 21,
80
- "F": 22,
81
- "G": 23,
82
- "H": 24,
83
  "I": 25,
84
- "J": 26,
85
- "K": 27,
86
- "L": 28,
87
- "M": 29,
88
- "N": 30,
89
  "O": 31,
90
- "P": 32,
91
  "Q": 33,
92
- "R": 34,
93
  "S": 35,
94
  "T": 36,
95
- "U": 37,
96
- "V": 38,
97
  "W": 39,
98
- "X": 40,
99
  "Y": 41,
100
- "Z": 42,
101
  "a": 43,
102
  "b": 44,
103
  "c": 45,
104
  "d": 46,
105
  "e": 47,
106
  "f": 48,
107
- "g": 49,
108
  "h": 50,
109
  "i": 51,
110
  "j": 52,
@@ -128,43 +115,23 @@
128
  "\u0250": 70,
129
  "\u0252": 71,
130
  "\u00e6": 72,
131
- "\u0253": 73,
132
- "\u0299": 74,
133
  "\u03b2": 75,
134
  "\u0254": 76,
135
  "\u0255": 77,
136
  "\u00e7": 78,
137
- "\u0257": 79,
138
  "\u0256": 80,
139
  "\u00f0": 81,
140
  "\u02a4": 82,
141
  "\u0259": 83,
142
- "\u0258": 84,
143
  "\u025a": 85,
144
  "\u025b": 86,
145
  "\u025c": 87,
146
- "\u025d": 88,
147
- "\u025e": 89,
148
  "\u025f": 90,
149
- "\u0284": 91,
150
  "\u0261": 92,
151
- "\u0260": 93,
152
- "\u0262": 94,
153
- "\u029b": 95,
154
- "\u0266": 96,
155
- "\u0267": 97,
156
- "\u0127": 98,
157
  "\u0265": 99,
158
- "\u029c": 100,
159
  "\u0268": 101,
160
  "\u026a": 102,
161
  "\u029d": 103,
162
- "\u026d": 104,
163
- "\u026c": 105,
164
- "\u026b": 106,
165
- "\u026e": 107,
166
- "\u029f": 108,
167
- "\u0271": 109,
168
  "\u026f": 110,
169
  "\u0270": 111,
170
  "\u014b": 112,
@@ -172,65 +139,36 @@
172
  "\u0272": 114,
173
  "\u0274": 115,
174
  "\u00f8": 116,
175
- "\u0275": 117,
176
  "\u0278": 118,
177
  "\u03b8": 119,
178
  "\u0153": 120,
179
- "\u0276": 121,
180
- "\u0298": 122,
181
  "\u0279": 123,
182
- "\u027a": 124,
183
  "\u027e": 125,
184
  "\u027b": 126,
185
- "\u0280": 127,
186
  "\u0281": 128,
187
  "\u027d": 129,
188
  "\u0282": 130,
189
  "\u0283": 131,
190
  "\u0288": 132,
191
  "\u02a7": 133,
192
- "\u0289": 134,
193
  "\u028a": 135,
194
  "\u028b": 136,
195
- "\u2c71": 137,
196
  "\u028c": 138,
197
  "\u0263": 139,
198
  "\u0264": 140,
199
- "\u028d": 141,
200
  "\u03c7": 142,
201
  "\u028e": 143,
202
- "\u028f": 144,
203
- "\u0291": 145,
204
- "\u0290": 146,
205
  "\u0292": 147,
206
  "\u0294": 148,
207
- "\u02a1": 149,
208
- "\u0295": 150,
209
- "\u02a2": 151,
210
- "\u01c0": 152,
211
- "\u01c1": 153,
212
- "\u01c2": 154,
213
- "\u01c3": 155,
214
  "\u02c8": 156,
215
  "\u02cc": 157,
216
  "\u02d0": 158,
217
- "\u02d1": 159,
218
- "\u02bc": 160,
219
- "\u02b4": 161,
220
  "\u02b0": 162,
221
- "\u02b1": 163,
222
  "\u02b2": 164,
223
- "\u02b7": 165,
224
- "\u02e0": 166,
225
- "\u02e4": 167,
226
- "\u02de": 168,
227
  "\u2193": 169,
228
- "\u2191": 170,
229
  "\u2192": 171,
230
  "\u2197": 172,
231
  "\u2198": 173,
232
- "\u0329": 175,
233
- "'": 176,
234
  "\u1d7b": 177
235
  }
236
  }
 
6
  "normalizer": {
7
  "type": "Replace",
8
  "pattern": {
9
+ "Regex": "[^$;:,.!?\u2014\u2026\"()\u201c\u201d \u0303\u02a3\u02a5\u02a6\u02a8\u1d5d\uab67AIOQSTWY\u1d4aabcdefhijklmnopqrstuvwxyz\u0251\u0250\u0252\u00e6\u03b2\u0254\u0255\u00e7\u0256\u00f0\u02a4\u0259\u025a\u025b\u025c\u025f\u0261\u0265\u0268\u026a\u029d\u026f\u0270\u014b\u0273\u0272\u0274\u00f8\u0278\u03b8\u0153\u0279\u027e\u027b\u0281\u027d\u0282\u0283\u0288\u02a7\u028a\u028b\u028c\u0263\u0264\u03c7\u028e\u0292\u0294\u02c8\u02cc\u02d0\u02b0\u02b2\u2193\u2192\u2197\u2198\u1d7b]"
10
  },
11
  "content": ""
12
  },
 
62
  ".": 4,
63
  "!": 5,
64
  "?": 6,
 
 
65
  "\u2014": 9,
66
  "\u2026": 10,
67
  "\"": 11,
68
+ "(": 12,
69
+ ")": 13,
70
  "\u201c": 14,
71
  "\u201d": 15,
72
  " ": 16,
73
+ "\u0303": 17,
74
+ "\u02a3": 18,
75
+ "\u02a5": 19,
76
+ "\u02a6": 20,
77
+ "\u02a8": 21,
78
+ "\u1d5d": 22,
79
+ "\uab67": 23,
80
+ "A": 24,
81
  "I": 25,
 
 
 
 
 
82
  "O": 31,
 
83
  "Q": 33,
 
84
  "S": 35,
85
  "T": 36,
 
 
86
  "W": 39,
 
87
  "Y": 41,
88
+ "\u1d4a": 42,
89
  "a": 43,
90
  "b": 44,
91
  "c": 45,
92
  "d": 46,
93
  "e": 47,
94
  "f": 48,
 
95
  "h": 50,
96
  "i": 51,
97
  "j": 52,
 
115
  "\u0250": 70,
116
  "\u0252": 71,
117
  "\u00e6": 72,
 
 
118
  "\u03b2": 75,
119
  "\u0254": 76,
120
  "\u0255": 77,
121
  "\u00e7": 78,
 
122
  "\u0256": 80,
123
  "\u00f0": 81,
124
  "\u02a4": 82,
125
  "\u0259": 83,
 
126
  "\u025a": 85,
127
  "\u025b": 86,
128
  "\u025c": 87,
 
 
129
  "\u025f": 90,
 
130
  "\u0261": 92,
 
 
 
 
 
 
131
  "\u0265": 99,
 
132
  "\u0268": 101,
133
  "\u026a": 102,
134
  "\u029d": 103,
 
 
 
 
 
 
135
  "\u026f": 110,
136
  "\u0270": 111,
137
  "\u014b": 112,
 
139
  "\u0272": 114,
140
  "\u0274": 115,
141
  "\u00f8": 116,
 
142
  "\u0278": 118,
143
  "\u03b8": 119,
144
  "\u0153": 120,
 
 
145
  "\u0279": 123,
 
146
  "\u027e": 125,
147
  "\u027b": 126,
 
148
  "\u0281": 128,
149
  "\u027d": 129,
150
  "\u0282": 130,
151
  "\u0283": 131,
152
  "\u0288": 132,
153
  "\u02a7": 133,
 
154
  "\u028a": 135,
155
  "\u028b": 136,
 
156
  "\u028c": 138,
157
  "\u0263": 139,
158
  "\u0264": 140,
 
159
  "\u03c7": 142,
160
  "\u028e": 143,
 
 
 
161
  "\u0292": 147,
162
  "\u0294": 148,
 
 
 
 
 
 
 
163
  "\u02c8": 156,
164
  "\u02cc": 157,
165
  "\u02d0": 158,
 
 
 
166
  "\u02b0": 162,
 
167
  "\u02b2": 164,
 
 
 
 
168
  "\u2193": 169,
 
169
  "\u2192": 171,
170
  "\u2197": 172,
171
  "\u2198": 173,
 
 
172
  "\u1d7b": 177
173
  }
174
  }