Create vocab.json
Browse files- vocab.json +274 -0
vocab.json
ADDED
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 0,
|
3 |
+
"<s>": 1,
|
4 |
+
"</s>": 2,
|
5 |
+
"<0x00>": 3,
|
6 |
+
"<0x01>": 4,
|
7 |
+
"<0x02>": 5,
|
8 |
+
"<0x03>": 6,
|
9 |
+
"<0x04>": 7,
|
10 |
+
"<0x05>": 8,
|
11 |
+
"<0x06>": 9,
|
12 |
+
"<0x07>": 10,
|
13 |
+
"<0x08>": 11,
|
14 |
+
"<0x09>": 12,
|
15 |
+
"<0x0A>": 13,
|
16 |
+
"<0x0B>": 14,
|
17 |
+
"<0x0C>": 15,
|
18 |
+
"<0x0D>": 16,
|
19 |
+
"<0x0E>": 17,
|
20 |
+
"<0x0F>": 18,
|
21 |
+
"<0x10>": 19,
|
22 |
+
"<0x11>": 20,
|
23 |
+
"<0x12>": 21,
|
24 |
+
"<0x13>": 22,
|
25 |
+
"<0x14>": 23,
|
26 |
+
"<0x15>": 24,
|
27 |
+
"<0x16>": 25,
|
28 |
+
"<0x17>": 26,
|
29 |
+
"<0x18>": 27,
|
30 |
+
"<0x19>": 28,
|
31 |
+
"<0x1A>": 29,
|
32 |
+
"<0x1B>": 30,
|
33 |
+
"<0x1C>": 31,
|
34 |
+
"<0x1D>": 32,
|
35 |
+
"<0x1E>": 33,
|
36 |
+
"<0x1F>": 34,
|
37 |
+
"<0x20>": 35,
|
38 |
+
"<0x21>": 36,
|
39 |
+
"<0x22>": 37,
|
40 |
+
"<0x23>": 38,
|
41 |
+
"<0x24>": 39,
|
42 |
+
"<0x25>": 40,
|
43 |
+
"<0x26>": 41,
|
44 |
+
"<0x27>": 42,
|
45 |
+
"<0x28>": 43,
|
46 |
+
"<0x29>": 44,
|
47 |
+
"<0x2A>": 45,
|
48 |
+
"<0x2B>": 46,
|
49 |
+
"<0x2C>": 47,
|
50 |
+
"<0x2D>": 48,
|
51 |
+
"<0x2E>": 49,
|
52 |
+
"<0x2F>": 50,
|
53 |
+
"<0x30>": 51,
|
54 |
+
"<0x31>": 52,
|
55 |
+
"<0x32>": 53,
|
56 |
+
"<0x33>": 54,
|
57 |
+
"<0x34>": 55,
|
58 |
+
"<0x35>": 56,
|
59 |
+
"<0x36>": 57,
|
60 |
+
"<0x37>": 58,
|
61 |
+
"<0x38>": 59,
|
62 |
+
"<0x39>": 60,
|
63 |
+
"<0x3A>": 61,
|
64 |
+
"<0x3B>": 62,
|
65 |
+
"<0x3C>": 63,
|
66 |
+
"<0x3D>": 64,
|
67 |
+
"<0x3E>": 65,
|
68 |
+
"<0x3F>": 66,
|
69 |
+
"<0x40>": 67,
|
70 |
+
"<0x41>": 68,
|
71 |
+
"<0x42>": 69,
|
72 |
+
"<0x43>": 70,
|
73 |
+
"<0x44>": 71,
|
74 |
+
"<0x45>": 72,
|
75 |
+
"<0x46>": 73,
|
76 |
+
"<0x47>": 74,
|
77 |
+
"<0x48>": 75,
|
78 |
+
"<0x49>": 76,
|
79 |
+
"<0x4A>": 77,
|
80 |
+
"<0x4B>": 78,
|
81 |
+
"<0x4C>": 79,
|
82 |
+
"<0x4D>": 80,
|
83 |
+
"<0x4E>": 81,
|
84 |
+
"<0x4F>": 82,
|
85 |
+
"<0x50>": 83,
|
86 |
+
"<0x51>": 84,
|
87 |
+
"<0x52>": 85,
|
88 |
+
"<0x53>": 86,
|
89 |
+
"<0x54>": 87,
|
90 |
+
"<0x55>": 88,
|
91 |
+
"<0x56>": 89,
|
92 |
+
"<0x57>": 90,
|
93 |
+
"<0x58>": 91,
|
94 |
+
"<0x59>": 92,
|
95 |
+
"<0x5A>": 93,
|
96 |
+
"<0x5B>": 94,
|
97 |
+
"<0x5C>": 95,
|
98 |
+
"<0x5D>": 96,
|
99 |
+
"<0x5E>": 97,
|
100 |
+
"<0x5F>": 98,
|
101 |
+
"<0x60>": 99,
|
102 |
+
"<0x61>": 100,
|
103 |
+
"<0x62>": 101,
|
104 |
+
"<0x63>": 102,
|
105 |
+
"<0x64>": 103,
|
106 |
+
"<0x65>": 104,
|
107 |
+
"<0x66>": 105,
|
108 |
+
"<0x67>": 106,
|
109 |
+
"<0x68>": 107,
|
110 |
+
"<0x69>": 108,
|
111 |
+
"<0x6A>": 109,
|
112 |
+
"<0x6B>": 110,
|
113 |
+
"<0x6C>": 111,
|
114 |
+
"<0x6D>": 112,
|
115 |
+
"<0x6E>": 113,
|
116 |
+
"<0x6F>": 114,
|
117 |
+
"<0x70>": 115,
|
118 |
+
"<0x71>": 116,
|
119 |
+
"<0x72>": 117,
|
120 |
+
"<0x73>": 118,
|
121 |
+
"<0x74>": 119,
|
122 |
+
"<0x75>": 120,
|
123 |
+
"<0x76>": 121,
|
124 |
+
"<0x77>": 122,
|
125 |
+
"<0x78>": 123,
|
126 |
+
"<0x79>": 124,
|
127 |
+
"<0x7A>": 125,
|
128 |
+
"<0x7B>": 126,
|
129 |
+
"<0x7C>": 127,
|
130 |
+
"<0x7D>": 128,
|
131 |
+
"<0x7E>": 129,
|
132 |
+
"<0x7F>": 130,
|
133 |
+
"<0x80>": 131,
|
134 |
+
"<0x81>": 132,
|
135 |
+
"<0x82>": 133,
|
136 |
+
"<0x83>": 134,
|
137 |
+
"<0x84>": 135,
|
138 |
+
"<0x85>": 136,
|
139 |
+
"<0x86>": 137,
|
140 |
+
"<0x87>": 138,
|
141 |
+
"<0x88>": 139,
|
142 |
+
"<0x89>": 140,
|
143 |
+
"<0x8A>": 141,
|
144 |
+
"<0x8B>": 142,
|
145 |
+
"<0x8C>": 143,
|
146 |
+
"<0x8D>": 144,
|
147 |
+
"<0x8E>": 145,
|
148 |
+
"<0x8F>": 146,
|
149 |
+
"<0x90>": 147,
|
150 |
+
"<0x91>": 148,
|
151 |
+
"<0x92>": 149,
|
152 |
+
"<0x93>": 150,
|
153 |
+
"<0x94>": 151,
|
154 |
+
"<0x95>": 152,
|
155 |
+
"<0x96>": 153,
|
156 |
+
"<0x97>": 154,
|
157 |
+
"<0x98>": 155,
|
158 |
+
"<0x99>": 156,
|
159 |
+
"<0x9A>": 157,
|
160 |
+
"<0x9B>": 158,
|
161 |
+
"<0x9C>": 159,
|
162 |
+
"<0x9D>": 160,
|
163 |
+
"<0x9E>": 161,
|
164 |
+
"<0x9F>": 162,
|
165 |
+
"<0xA0>": 163,
|
166 |
+
"<0xA1>": 164,
|
167 |
+
"<0xA2>": 165,
|
168 |
+
"<0xA3>": 166,
|
169 |
+
"<0xA4>": 167,
|
170 |
+
"<0xA5>": 168,
|
171 |
+
"<0xA6>": 169,
|
172 |
+
"<0xA7>": 170,
|
173 |
+
"<0xA8>": 171,
|
174 |
+
"<0xA9>": 172,
|
175 |
+
"<0xAA>": 173,
|
176 |
+
"<0xAB>": 174,
|
177 |
+
"<0xAC>": 175,
|
178 |
+
"<0xAD>": 176,
|
179 |
+
"<0xAE>": 177,
|
180 |
+
"<0xAF>": 178,
|
181 |
+
"<0xB0>": 179,
|
182 |
+
"<0xB1>": 180,
|
183 |
+
"<0xB2>": 181,
|
184 |
+
"<0xB3>": 182,
|
185 |
+
"<0xB4>": 183,
|
186 |
+
"<0xB5>": 184,
|
187 |
+
"<0xB6>": 185,
|
188 |
+
"<0xB7>": 186,
|
189 |
+
"<0xB8>": 187,
|
190 |
+
"<0xB9>": 188,
|
191 |
+
"<0xBA>": 189,
|
192 |
+
"<0xBB>": 190,
|
193 |
+
"<0xBC>": 191,
|
194 |
+
"<0xBD>": 192,
|
195 |
+
"<0xBE>": 193,
|
196 |
+
"<0xBF>": 194,
|
197 |
+
"<0xC0>": 195,
|
198 |
+
"<0xC1>": 196,
|
199 |
+
"<0xC2>": 197,
|
200 |
+
"<0xC3>": 198,
|
201 |
+
"<0xC4>": 199,
|
202 |
+
"<0xC5>": 200,
|
203 |
+
"<0xC6>": 201,
|
204 |
+
"<0xC7>": 202,
|
205 |
+
"<0xC8>": 203,
|
206 |
+
"<0xC9>": 204,
|
207 |
+
"<0xCA>": 205,
|
208 |
+
"<0xCB>": 206,
|
209 |
+
"<0xCC>": 207,
|
210 |
+
"<0xCD>": 208,
|
211 |
+
"<0xCE>": 209,
|
212 |
+
"<0xCF>": 210,
|
213 |
+
"<0xD0>": 211,
|
214 |
+
"<0xD1>": 212,
|
215 |
+
"<0xD2>": 213,
|
216 |
+
"<0xD3>": 214,
|
217 |
+
"<0xD4>": 215,
|
218 |
+
"<0xD5>": 216,
|
219 |
+
"<0xD6>": 217,
|
220 |
+
"<0xD7>": 218,
|
221 |
+
"<0xD8>": 219,
|
222 |
+
"<0xD9>": 220,
|
223 |
+
"<0xDA>": 221,
|
224 |
+
"<0xDB>": 222,
|
225 |
+
"<0xDC>": 223,
|
226 |
+
"<0xDD>": 224,
|
227 |
+
"<0xDE>": 225,
|
228 |
+
"<0xDF>": 226,
|
229 |
+
"<0xE0>": 227,
|
230 |
+
"<0xE1>": 228,
|
231 |
+
"<0xE2>": 229,
|
232 |
+
"<0xE3>": 230,
|
233 |
+
"<0xE4>": 231,
|
234 |
+
"<0xE5>": 232,
|
235 |
+
"<0xE6>": 233,
|
236 |
+
"<0xE7>": 234,
|
237 |
+
"<0xE8>": 235,
|
238 |
+
"<0xE9>": 236,
|
239 |
+
"<0xEA>": 237,
|
240 |
+
"<0xEB>": 238,
|
241 |
+
"<0xEC>": 239,
|
242 |
+
"<0xED>": 240,
|
243 |
+
"<0xEE>": 241,
|
244 |
+
"<0xEF>": 242,
|
245 |
+
"<0xF0>": 243,
|
246 |
+
"<0xF1>": 244,
|
247 |
+
"<0xF2>": 245,
|
248 |
+
"<0xF3>": 246,
|
249 |
+
"<0xF4>": 247,
|
250 |
+
"<0xF5>": 248,
|
251 |
+
"<0xF6>": 249,
|
252 |
+
"<0xF7>": 250,
|
253 |
+
"<0xF8>": 251,
|
254 |
+
"<0xF9>": 252,
|
255 |
+
"<0xFA>": 253,
|
256 |
+
"<0xFB>": 254,
|
257 |
+
"<0xFC>": 255,
|
258 |
+
"<0xFD>": 256,
|
259 |
+
"<0xFE>": 257,
|
260 |
+
"<0xFF>": 258,
|
261 |
+
"β": 259,
|
262 |
+
"ββ": 260,
|
263 |
+
"βββ": 261,
|
264 |
+
"ββββ": 262,
|
265 |
+
"βββββ": 263,
|
266 |
+
"ββββββ": 264,
|
267 |
+
"βββββββ": 265,
|
268 |
+
"ββββββββ": 266,
|
269 |
+
"βt": 267,
|
270 |
+
"in": 268,
|
271 |
+
"er": 269,
|
272 |
+
"βa": 270,
|
273 |
+
"he": 271
|
274 |
+
}
|