mms-1b-all-AmhLM / vocab.json
jlonsako's picture
Upload lm-boosted decoder
8158e87
{
"!": 297,
"\"": 242,
"$": 256,
"%": 264,
"&": 303,
"'": 293,
"+": 276,
",": 194,
"-": 142,
".": 138,
"/": 208,
"0": 64,
"1": 77,
"2": 104,
"3": 153,
"4": 149,
"5": 144,
"6": 157,
"7": 180,
"8": 159,
"9": 139,
":": 243,
";": 286,
"</s>": 2,
"<pad>": 0,
"<s>": 1,
"<unk>": 3,
"?": 273,
"[": 306,
"]": 307,
"a": 113,
"b": 205,
"c": 173,
"d": 203,
"e": 146,
"f": 218,
"g": 197,
"h": 186,
"i": 152,
"j": 238,
"k": 217,
"l": 165,
"m": 182,
"n": 141,
"o": 135,
"p": 183,
"q": 302,
"r": 158,
"s": 164,
"t": 160,
"u": 175,
"v": 227,
"w": 226,
"x": 255,
"y": 221,
"z": 266,
"|": 4,
"ยฃ": 304,
"ยฅ": 288,
"ยซ": 260,
"ยฐ": 279,
"ยฒ": 298,
"ยป": 261,
"รฃ": 287,
"รต": 283,
"แˆ€": 123,
"แˆ": 63,
"แˆ‚": 184,
"แˆƒ": 95,
"แˆ„": 137,
"แˆ…": 51,
"แˆ†": 48,
"แˆˆ": 18,
"แˆ‰": 43,
"แˆŠ": 61,
"แˆ‹": 24,
"แˆŒ": 82,
"แˆ": 13,
"แˆŽ": 62,
"แˆ": 185,
"แˆ": 189,
"แˆ‘": 235,
"แˆ’": 338,
"แˆ“": 313,
"แˆ”": 233,
"แˆ•": 130,
"แˆ–": 331,
"แˆ˜": 12,
"แˆ™": 117,
"แˆš": 38,
"แˆ›": 29,
"แˆœ": 89,
"แˆ": 14,
"แˆž": 79,
"แˆŸ": 212,
"แˆ ": 174,
"แˆก": 316,
"แˆข": 336,
"แˆฃ": 228,
"แˆค": 321,
"แˆฅ": 132,
"แˆฆ": 229,
"แˆจ": 30,
"แˆฉ": 65,
"แˆช": 44,
"แˆซ": 35,
"แˆฌ": 111,
"แˆญ": 11,
"แˆฎ": 58,
"แˆฏ": 196,
"แˆฐ": 36,
"แˆฑ": 112,
"แˆฒ": 70,
"แˆณ": 47,
"แˆด": 134,
"แˆต": 10,
"แˆถ": 119,
"แˆท": 223,
"แˆธ": 145,
"แˆน": 207,
"แˆบ": 192,
"แˆป": 121,
"แˆผ": 275,
"แˆฝ": 86,
"แˆพ": 209,
"แˆฟ": 280,
"แ‰€": 42,
"แ‰": 105,
"แ‰‚": 147,
"แ‰ƒ": 67,
"แ‰„": 219,
"แ‰…": 50,
"แ‰†": 107,
"แ‰ˆ": 310,
"แ‰Š": 315,
"แ‰‹": 116,
"แ‰": 314,
"แ‰ ": 6,
"แ‰ก": 92,
"แ‰ข": 72,
"แ‰ฃ": 40,
"แ‰ค": 97,
"แ‰ฅ": 28,
"แ‰ฆ": 80,
"แ‰ง": 210,
"แ‰จ": 206,
"แ‰ช": 168,
"แ‰ซ": 190,
"แ‰ฌ": 211,
"แ‰ญ": 213,
"แ‰ฎ": 259,
"แ‰ฐ": 19,
"แ‰ฑ": 66,
"แ‰ฒ": 114,
"แ‰ณ": 34,
"แ‰ด": 129,
"แ‰ต": 7,
"แ‰ถ": 56,
"แ‰ท": 169,
"แ‰ธ": 55,
"แ‰น": 103,
"แ‰บ": 220,
"แ‰ป": 98,
"แ‰ผ": 241,
"แ‰ฝ": 15,
"แ‰พ": 232,
"แ‰ฟ": 299,
"แŠ€": 309,
"แŠƒ": 172,
"แŠ„": 328,
"แŠ…": 251,
"แŠ†": 330,
"แŠ‹": 150,
"แŠ": 21,
"แŠ‘": 83,
"แŠ’": 99,
"แŠ“": 23,
"แŠ”": 118,
"แŠ•": 5,
"แŠ–": 69,
"แŠ—": 237,
"แŠ˜": 154,
"แŠ™": 163,
"แŠš": 244,
"แŠ›": 57,
"แŠœ": 292,
"แŠ": 124,
"แŠž": 179,
"แŠŸ": 305,
"แŠ ": 17,
"แŠก": 257,
"แŠข": 126,
"แŠฃ": 252,
"แŠค": 115,
"แŠฅ": 20,
"แŠฆ": 143,
"แŠจ": 25,
"แŠฉ": 136,
"แŠช": 110,
"แŠซ": 46,
"แŠฌ": 176,
"แŠญ": 39,
"แŠฎ": 88,
"แŠฐ": 300,
"แŠณ": 181,
"แŠต": 312,
"แŠธ": 285,
"แŠน": 319,
"แŠบ": 289,
"แŠป": 324,
"แŠฝ": 323,
"แŠพ": 320,
"แ‹ˆ": 33,
"แ‹‰": 250,
"แ‹Š": 74,
"แ‹‹": 53,
"แ‹Œ": 200,
"แ‹": 9,
"แ‹Ž": 41,
"แ‹": 240,
"แ‹‘": 249,
"แ‹’": 278,
"แ‹“": 90,
"แ‹”": 325,
"แ‹•": 101,
"แ‹–": 281,
"แ‹˜": 71,
"แ‹™": 87,
"แ‹š": 91,
"แ‹›": 84,
"แ‹œ": 81,
"แ‹": 68,
"แ‹ž": 167,
"แ‹Ÿ": 265,
"แ‹ ": 332,
"แ‹ก": 267,
"แ‹ข": 248,
"แ‹ฃ": 231,
"แ‹ค": 329,
"แ‹ฅ": 201,
"แ‹ฆ": 245,
"แ‹จ": 8,
"แ‹ฉ": 100,
"แ‹ช": 272,
"แ‹ซ": 22,
"แ‹ฌ": 225,
"แ‹ญ": 16,
"แ‹ฎ": 128,
"แ‹ฐ": 26,
"แ‹ฑ": 108,
"แ‹ฒ": 75,
"แ‹ณ": 52,
"แ‹ด": 177,
"แ‹ต": 27,
"แ‹ถ": 94,
"แ‹ท": 246,
"แŒ€": 85,
"แŒ": 202,
"แŒ‚": 166,
"แŒƒ": 133,
"แŒ„": 224,
"แŒ…": 109,
"แŒ†": 171,
"แŒ‡": 294,
"แŒˆ": 32,
"แŒ‰": 78,
"แŒŠ": 76,
"แŒ‹": 54,
"แŒŒ": 230,
"แŒ": 31,
"แŒŽ": 96,
"แŒ": 282,
"แŒ’": 311,
"แŒ“": 140,
"แŒ•": 322,
"แŒ ": 45,
"แŒก": 151,
"แŒข": 258,
"แŒฃ": 59,
"แŒค": 193,
"แŒฅ": 37,
"แŒฆ": 162,
"แŒง": 236,
"แŒจ": 102,
"แŒฉ": 234,
"แŒช": 216,
"แŒซ": 127,
"แŒฌ": 326,
"แŒญ": 131,
"แŒฎ": 239,
"แŒฏ": 333,
"แŒฐ": 335,
"แŒฑ": 334,
"แŒฒ": 317,
"แŒณ": 291,
"แŒด": 290,
"แŒต": 268,
"แŒถ": 318,
"แŒธ": 191,
"แŒน": 263,
"แŒบ": 295,
"แŒป": 199,
"แŒผ": 327,
"แŒฝ": 156,
"แŒพ": 254,
"แŒฟ": 271,
"แ€": 187,
"แ": 270,
"แƒ": 178,
"แ„": 337,
"แ…": 170,
"แ†": 253,
"แˆ": 60,
"แ‰": 161,
"แŠ": 93,
"แ‹": 106,
"แŒ": 195,
"แ": 49,
"แŽ": 148,
"แ": 222,
"แ": 204,
"แ‘": 262,
"แ’": 155,
"แ“": 120,
"แ”": 215,
"แ•": 122,
"แ–": 125,
"แ—": 301,
"แก": 198,
"แข": 188,
"แฃ": 73,
"แค": 247,
"แฅ": 277,
"แฆ": 308,
"โ€“": 284,
"โ€”": 269,
"โ€˜": 296,
"โ€™": 274,
"โ€": 214
}