Samuael's picture
Upload tokenizer
8231a2f verified
{
"[PAD]": 0,
"[UNK]": 1,
"|": 2,
"แˆˆ": 60,
"แˆ‰": 61,
"แˆŠ": 62,
"แˆ‹": 63,
"แˆŒ": 64,
"แˆ": 240,
"แˆŽ": 65,
"แˆ": 4,
"แˆ‘": 56,
"แˆ’": 57,
"แˆ“": 55,
"แˆ”": 58,
"แˆ•": 241,
"แˆ–": 59,
"แˆ˜": 66,
"แˆ™": 67,
"แˆš": 68,
"แˆ›": 69,
"แˆœ": 70,
"แˆ": 242,
"แˆž": 71,
"แˆŸ": 5,
"แˆจ": 72,
"แˆฉ": 73,
"แˆช": 74,
"แˆซ": 75,
"แˆฌ": 76,
"แˆญ": 243,
"แˆฎ": 77,
"แˆฏ": 6,
"แˆฐ": 78,
"แˆฑ": 79,
"แˆฒ": 80,
"แˆณ": 81,
"แˆด": 82,
"แˆต": 244,
"แˆถ": 83,
"แˆท": 7,
"แˆธ": 84,
"แˆน": 85,
"แˆบ": 86,
"แˆป": 87,
"แˆผ": 88,
"แˆฝ": 245,
"แˆพ": 89,
"แˆฟ": 8,
"แ‰€": 90,
"แ‰": 91,
"แ‰‚": 92,
"แ‰ƒ": 93,
"แ‰„": 94,
"แ‰…": 246,
"แ‰†": 95,
"แ‰ˆ": 99,
"แ‰Š": 97,
"แ‰‹": 9,
"แ‰Œ": 96,
"แ‰": 98,
"แ‰": 100,
"แ‰‘": 101,
"แ‰’": 102,
"แ‰“": 103,
"แ‰”": 104,
"แ‰•": 247,
"แ‰–": 105,
"แ‰˜": 45,
"แ‰š": 46,
"แ‰›": 47,
"แ‰œ": 48,
"แ‰ ": 106,
"แ‰ก": 107,
"แ‰ข": 108,
"แ‰ฃ": 109,
"แ‰ค": 110,
"แ‰ฅ": 248,
"แ‰ฆ": 111,
"แ‰ง": 10,
"แ‰จ": 112,
"แ‰ฉ": 113,
"แ‰ช": 114,
"แ‰ซ": 115,
"แ‰ฌ": 116,
"แ‰ญ": 249,
"แ‰ฎ": 117,
"แ‰ฏ": 11,
"แ‰ฐ": 118,
"แ‰ฑ": 119,
"แ‰ฒ": 120,
"แ‰ณ": 121,
"แ‰ด": 122,
"แ‰ต": 250,
"แ‰ถ": 123,
"แ‰ท": 12,
"แ‰ธ": 124,
"แ‰น": 125,
"แ‰บ": 126,
"แ‰ป": 127,
"แ‰ผ": 128,
"แ‰ฝ": 251,
"แ‰พ": 129,
"แ‰ฟ": 13,
"แŠŠ": 33,
"แŠ‹": 3,
"แŠŒ": 30,
"แŠ": 130,
"แŠ‘": 131,
"แŠ’": 132,
"แŠ“": 133,
"แŠ”": 134,
"แŠ•": 252,
"แŠ–": 135,
"แŠ—": 14,
"แŠ˜": 136,
"แŠ™": 137,
"แŠš": 138,
"แŠ›": 139,
"แŠœ": 140,
"แŠ": 253,
"แŠž": 141,
"แŠŸ": 15,
"แŠก": 50,
"แŠข": 51,
"แŠฃ": 254,
"แŠค": 52,
"แŠฅ": 53,
"แŠฆ": 54,
"แŠง": 49,
"แŠจ": 142,
"แŠฉ": 143,
"แŠช": 144,
"แŠซ": 145,
"แŠฌ": 146,
"แŠญ": 255,
"แŠฎ": 147,
"แŠฐ": 148,
"แŠฒ": 32,
"แŠณ": 16,
"แŠด": 29,
"แŠต": 149,
"แŠธ": 150,
"แŠน": 151,
"แŠบ": 152,
"แŠป": 153,
"แŠผ": 154,
"แŠฝ": 256,
"แŠพ": 155,
"แ‹€": 156,
"แ‹‚": 159,
"แ‹ƒ": 157,
"แ‹„": 158,
"แ‹…": 160,
"แ‹ˆ": 161,
"แ‹‰": 162,
"แ‹Š": 163,
"แ‹‹": 164,
"แ‹Œ": 165,
"แ‹": 257,
"แ‹Ž": 166,
"แ‹˜": 167,
"แ‹™": 168,
"แ‹š": 169,
"แ‹›": 170,
"แ‹œ": 171,
"แ‹": 258,
"แ‹ž": 172,
"แ‹Ÿ": 17,
"แ‹ ": 173,
"แ‹ก": 174,
"แ‹ข": 175,
"แ‹ฃ": 176,
"แ‹ค": 177,
"แ‹ฅ": 259,
"แ‹ฆ": 178,
"แ‹ง": 18,
"แ‹จ": 179,
"แ‹ฉ": 180,
"แ‹ช": 181,
"แ‹ซ": 182,
"แ‹ฌ": 183,
"แ‹ญ": 260,
"แ‹ฎ": 184,
"แ‹ฐ": 185,
"แ‹ฑ": 186,
"แ‹ฒ": 187,
"แ‹ณ": 188,
"แ‹ด": 189,
"แ‹ต": 261,
"แ‹ถ": 190,
"แ‹ท": 19,
"แŒ€": 191,
"แŒ": 192,
"แŒ‚": 193,
"แŒƒ": 194,
"แŒ„": 195,
"แŒ…": 262,
"แŒ†": 196,
"แŒ‡": 20,
"แŒˆ": 197,
"แŒ‰": 198,
"แŒŠ": 199,
"แŒ‹": 200,
"แŒŒ": 201,
"แŒ": 263,
"แŒŽ": 202,
"แŒ": 203,
"แŒ’": 31,
"แŒ“": 21,
"แŒ”": 28,
"แŒ•": 35,
"แŒ ": 204,
"แŒก": 205,
"แŒข": 206,
"แŒฃ": 207,
"แŒค": 208,
"แŒฅ": 264,
"แŒฆ": 209,
"แŒง": 22,
"แŒจ": 210,
"แŒฉ": 211,
"แŒช": 212,
"แŒซ": 213,
"แŒฌ": 214,
"แŒญ": 265,
"แŒฎ": 215,
"แŒฏ": 23,
"แŒฐ": 216,
"แŒฑ": 217,
"แŒฒ": 218,
"แŒณ": 219,
"แŒด": 220,
"แŒต": 266,
"แŒถ": 221,
"แŒท": 24,
"แŒธ": 222,
"แŒน": 223,
"แŒบ": 224,
"แŒป": 225,
"แŒผ": 226,
"แŒฝ": 267,
"แŒพ": 227,
"แŒฟ": 25,
"แˆ": 228,
"แ‰": 229,
"แŠ": 230,
"แ‹": 231,
"แŒ": 232,
"แ": 268,
"แŽ": 233,
"แ": 26,
"แ": 234,
"แ‘": 235,
"แ’": 236,
"แ“": 237,
"แ”": 238,
"แ•": 269,
"แ–": 239,
"แ—": 27,
"แ˜": 40,
"แ™": 36,
"แš": 37,
"แŽ‰": 34,
"แŽŠ": 38,
"แŽ‹": 39,
"แŽŒ": 41,
"แŽ": 42,
"แŽŽ": 43,
"แŽ": 44
}