timotewos's picture
Upload tokenizer
7a5d044 verified
raw
history blame
3.12 kB
{
"[PAD]": 229,
"[UNK]": 228,
"|": 95,
"แˆ€": 116,
"แˆ": 63,
"แˆ‚": 145,
"แˆƒ": 183,
"แˆ„": 53,
"แˆ…": 37,
"แˆ†": 159,
"แˆˆ": 226,
"แˆ‰": 78,
"แˆŠ": 107,
"แˆ‹": 61,
"แˆŒ": 72,
"แˆ": 149,
"แˆŽ": 22,
"แˆ": 99,
"แˆ": 219,
"แˆ‘": 160,
"แˆ“": 196,
"แˆ”": 9,
"แˆ•": 157,
"แˆ˜": 48,
"แˆ™": 17,
"แˆš": 195,
"แˆ›": 39,
"แˆœ": 127,
"แˆ": 190,
"แˆž": 222,
"แˆŸ": 203,
"แˆ ": 85,
"แˆก": 65,
"แˆฃ": 79,
"แˆฅ": 57,
"แˆฆ": 29,
"แˆจ": 20,
"แˆฉ": 4,
"แˆช": 7,
"แˆซ": 15,
"แˆฌ": 46,
"แˆญ": 100,
"แˆฎ": 102,
"แˆฏ": 164,
"แˆฐ": 6,
"แˆฑ": 64,
"แˆฒ": 121,
"แˆณ": 197,
"แˆด": 144,
"แˆต": 211,
"แˆถ": 131,
"แˆท": 94,
"แˆธ": 119,
"แˆน": 176,
"แˆบ": 166,
"แˆป": 174,
"แˆผ": 26,
"แˆฝ": 44,
"แˆพ": 153,
"แ‰€": 224,
"แ‰": 177,
"แ‰‚": 62,
"แ‰ƒ": 191,
"แ‰„": 210,
"แ‰…": 129,
"แ‰†": 104,
"แ‰‹": 214,
"แ‰ ": 185,
"แ‰ก": 120,
"แ‰ข": 54,
"แ‰ฃ": 49,
"แ‰ค": 70,
"แ‰ฅ": 147,
"แ‰ฆ": 83,
"แ‰ง": 77,
"แ‰จ": 113,
"แ‰ช": 123,
"แ‰ซ": 122,
"แ‰ญ": 223,
"แ‰ฎ": 68,
"แ‰ฐ": 167,
"แ‰ฑ": 182,
"แ‰ฒ": 171,
"แ‰ณ": 126,
"แ‰ด": 106,
"แ‰ต": 134,
"แ‰ถ": 59,
"แ‰ท": 199,
"แ‰ธ": 24,
"แ‰น": 221,
"แ‰บ": 8,
"แ‰ป": 154,
"แ‰ผ": 19,
"แ‰ฝ": 165,
"แ‰พ": 12,
"แ‰ฟ": 140,
"แŠ€": 208,
"แŠƒ": 115,
"แŠ…": 5,
"แŠ‹": 118,
"แŠ": 97,
"แŠ‘": 58,
"แŠ’": 10,
"แŠ“": 227,
"แŠ”": 55,
"แŠ•": 148,
"แŠ–": 28,
"แŠ—": 80,
"แŠ˜": 67,
"แŠ™": 96,
"แŠ›": 27,
"แŠ": 212,
"แŠž": 218,
"แŠŸ": 117,
"แŠ ": 84,
"แŠก": 41,
"แŠข": 14,
"แŠค": 193,
"แŠฅ": 88,
"แŠฆ": 152,
"แŠจ": 173,
"แŠฉ": 13,
"แŠช": 2,
"แŠซ": 109,
"แŠฌ": 69,
"แŠญ": 23,
"แŠฎ": 43,
"แŠณ": 137,
"แŠธ": 25,
"แŠฝ": 142,
"แ‹ˆ": 101,
"แ‹Š": 132,
"แ‹‹": 216,
"แ‹Œ": 112,
"แ‹": 128,
"แ‹Ž": 42,
"แ‹": 11,
"แ‹‘": 0,
"แ‹’": 207,
"แ‹“": 3,
"แ‹•": 81,
"แ‹–": 178,
"แ‹˜": 151,
"แ‹™": 133,
"แ‹š": 74,
"แ‹›": 56,
"แ‹œ": 40,
"แ‹": 47,
"แ‹ž": 52,
"แ‹Ÿ": 21,
"แ‹ข": 31,
"แ‹ฃ": 181,
"แ‹ค": 188,
"แ‹ฅ": 206,
"แ‹ฆ": 73,
"แ‹จ": 45,
"แ‹ฉ": 201,
"แ‹ซ": 170,
"แ‹ฌ": 33,
"แ‹ญ": 146,
"แ‹ฎ": 130,
"แ‹ฐ": 156,
"แ‹ฑ": 136,
"แ‹ฒ": 141,
"แ‹ณ": 213,
"แ‹ด": 50,
"แ‹ต": 111,
"แ‹ถ": 34,
"แ‹ท": 38,
"แŒ€": 198,
"แŒ": 187,
"แŒ‚": 172,
"แŒƒ": 150,
"แŒ„": 105,
"แŒ…": 124,
"แŒ†": 192,
"แŒˆ": 92,
"แŒ‰": 89,
"แŒŠ": 35,
"แŒ‹": 179,
"แŒŒ": 87,
"แŒ": 108,
"แŒŽ": 30,
"แŒ“": 202,
"แŒ ": 168,
"แŒก": 217,
"แŒข": 158,
"แŒฃ": 194,
"แŒค": 186,
"แŒฅ": 161,
"แŒฆ": 86,
"แŒง": 91,
"แŒจ": 36,
"แŒฉ": 135,
"แŒช": 51,
"แŒซ": 138,
"แŒฌ": 205,
"แŒญ": 163,
"แŒฎ": 114,
"แŒฒ": 66,
"แŒด": 32,
"แŒต": 200,
"แŒถ": 1,
"แŒธ": 90,
"แŒน": 16,
"แŒบ": 82,
"แŒป": 220,
"แŒฝ": 75,
"แŒพ": 209,
"แŒฟ": 169,
"แ€": 180,
"แ": 143,
"แƒ": 204,
"แ…": 184,
"แˆ": 189,
"แ‰": 110,
"แŠ": 162,
"แ‹": 98,
"แŒ": 125,
"แ": 155,
"แŽ": 76,
"แ": 93,
"แ‘": 103,
"แ’": 215,
"แ“": 71,
"แ”": 139,
"แ•": 60,
"แ–": 18,
"โ€œ": 175,
"โ€": 225
}