DipsankarSinha's picture
Upload tokenizer
966c33b verified
raw
history blame
3.12 kB
{
"[PAD]": 229,
"[UNK]": 228,
"|": 85,
"แˆ€": 203,
"แˆ": 39,
"แˆ‚": 72,
"แˆƒ": 174,
"แˆ„": 219,
"แˆ…": 66,
"แˆ†": 184,
"แˆˆ": 183,
"แˆ‰": 216,
"แˆŠ": 98,
"แˆ‹": 166,
"แˆŒ": 154,
"แˆ": 187,
"แˆŽ": 35,
"แˆ": 114,
"แˆ": 131,
"แˆ‘": 49,
"แˆ“": 180,
"แˆ”": 132,
"แˆ•": 226,
"แˆ˜": 198,
"แˆ™": 119,
"แˆš": 196,
"แˆ›": 59,
"แˆœ": 202,
"แˆ": 57,
"แˆž": 71,
"แˆŸ": 0,
"แˆ ": 109,
"แˆก": 122,
"แˆฃ": 77,
"แˆฅ": 116,
"แˆฆ": 88,
"แˆจ": 58,
"แˆฉ": 70,
"แˆช": 14,
"แˆซ": 76,
"แˆฌ": 204,
"แˆญ": 27,
"แˆฎ": 171,
"แˆฏ": 217,
"แˆฐ": 212,
"แˆฑ": 43,
"แˆฒ": 163,
"แˆณ": 169,
"แˆด": 56,
"แˆต": 182,
"แˆถ": 23,
"แˆท": 103,
"แˆธ": 127,
"แˆน": 106,
"แˆบ": 32,
"แˆป": 101,
"แˆผ": 30,
"แˆฝ": 197,
"แˆพ": 21,
"แ‰€": 210,
"แ‰": 55,
"แ‰‚": 65,
"แ‰ƒ": 102,
"แ‰„": 188,
"แ‰…": 11,
"แ‰†": 74,
"แ‰‹": 181,
"แ‰ ": 111,
"แ‰ก": 7,
"แ‰ข": 207,
"แ‰ฃ": 139,
"แ‰ค": 223,
"แ‰ฅ": 165,
"แ‰ฆ": 100,
"แ‰ง": 201,
"แ‰จ": 159,
"แ‰ช": 68,
"แ‰ซ": 199,
"แ‰ญ": 8,
"แ‰ฎ": 41,
"แ‰ฐ": 82,
"แ‰ฑ": 172,
"แ‰ฒ": 34,
"แ‰ณ": 177,
"แ‰ด": 117,
"แ‰ต": 225,
"แ‰ถ": 227,
"แ‰ท": 37,
"แ‰ธ": 90,
"แ‰น": 200,
"แ‰บ": 104,
"แ‰ป": 141,
"แ‰ผ": 113,
"แ‰ฝ": 209,
"แ‰พ": 164,
"แ‰ฟ": 222,
"แŠ€": 150,
"แŠƒ": 52,
"แŠ…": 173,
"แŠ‹": 220,
"แŠ": 193,
"แŠ‘": 135,
"แŠ’": 143,
"แŠ“": 15,
"แŠ”": 44,
"แŠ•": 81,
"แŠ–": 148,
"แŠ—": 221,
"แŠ˜": 208,
"แŠ™": 145,
"แŠ›": 170,
"แŠ": 29,
"แŠž": 5,
"แŠŸ": 142,
"แŠ ": 3,
"แŠก": 20,
"แŠข": 110,
"แŠค": 178,
"แŠฅ": 33,
"แŠฆ": 25,
"แŠจ": 38,
"แŠฉ": 153,
"แŠช": 179,
"แŠซ": 94,
"แŠฌ": 136,
"แŠญ": 138,
"แŠฎ": 50,
"แŠณ": 147,
"แŠธ": 19,
"แŠฝ": 31,
"แ‹ˆ": 97,
"แ‹Š": 93,
"แ‹‹": 121,
"แ‹Œ": 108,
"แ‹": 214,
"แ‹Ž": 62,
"แ‹": 186,
"แ‹‘": 137,
"แ‹’": 2,
"แ‹“": 10,
"แ‹•": 124,
"แ‹–": 1,
"แ‹˜": 73,
"แ‹™": 157,
"แ‹š": 206,
"แ‹›": 215,
"แ‹œ": 130,
"แ‹": 107,
"แ‹ž": 60,
"แ‹Ÿ": 118,
"แ‹ข": 140,
"แ‹ฃ": 61,
"แ‹ค": 91,
"แ‹ฅ": 89,
"แ‹ฆ": 112,
"แ‹จ": 51,
"แ‹ฉ": 167,
"แ‹ซ": 128,
"แ‹ฌ": 129,
"แ‹ญ": 125,
"แ‹ฎ": 47,
"แ‹ฐ": 195,
"แ‹ฑ": 176,
"แ‹ฒ": 156,
"แ‹ณ": 42,
"แ‹ด": 84,
"แ‹ต": 69,
"แ‹ถ": 78,
"แ‹ท": 146,
"แŒ€": 24,
"แŒ": 158,
"แŒ‚": 83,
"แŒƒ": 155,
"แŒ„": 87,
"แŒ…": 22,
"แŒ†": 80,
"แŒˆ": 95,
"แŒ‰": 189,
"แŒŠ": 86,
"แŒ‹": 211,
"แŒŒ": 9,
"แŒ": 26,
"แŒŽ": 99,
"แŒ“": 17,
"แŒ ": 126,
"แŒก": 4,
"แŒข": 133,
"แŒฃ": 18,
"แŒค": 205,
"แŒฅ": 185,
"แŒฆ": 96,
"แŒง": 175,
"แŒจ": 67,
"แŒฉ": 162,
"แŒช": 79,
"แŒซ": 192,
"แŒฌ": 40,
"แŒญ": 46,
"แŒฎ": 218,
"แŒฒ": 53,
"แŒด": 161,
"แŒต": 63,
"แŒถ": 168,
"แŒธ": 213,
"แŒน": 54,
"แŒบ": 123,
"แŒป": 160,
"แŒฝ": 28,
"แŒพ": 115,
"แŒฟ": 6,
"แ€": 12,
"แ": 151,
"แƒ": 48,
"แ…": 191,
"แˆ": 64,
"แ‰": 36,
"แŠ": 92,
"แ‹": 75,
"แŒ": 190,
"แ": 120,
"แŽ": 224,
"แ": 16,
"แ‘": 45,
"แ’": 194,
"แ“": 134,
"แ”": 149,
"แ•": 13,
"แ–": 152,
"โ€œ": 105,
"โ€": 144
}