DipsankarSinha's picture
Upload tokenizer
af09f07 verified
raw
history blame
3.12 kB
{
"[PAD]": 229,
"[UNK]": 228,
"|": 144,
"แˆ€": 78,
"แˆ": 165,
"แˆ‚": 120,
"แˆƒ": 77,
"แˆ„": 200,
"แˆ…": 142,
"แˆ†": 46,
"แˆˆ": 150,
"แˆ‰": 44,
"แˆŠ": 79,
"แˆ‹": 126,
"แˆŒ": 8,
"แˆ": 58,
"แˆŽ": 40,
"แˆ": 194,
"แˆ": 134,
"แˆ‘": 167,
"แˆ“": 164,
"แˆ”": 110,
"แˆ•": 102,
"แˆ˜": 184,
"แˆ™": 9,
"แˆš": 87,
"แˆ›": 148,
"แˆœ": 24,
"แˆ": 7,
"แˆž": 172,
"แˆŸ": 218,
"แˆ ": 220,
"แˆก": 176,
"แˆฃ": 141,
"แˆฅ": 27,
"แˆฆ": 192,
"แˆจ": 55,
"แˆฉ": 170,
"แˆช": 107,
"แˆซ": 22,
"แˆฌ": 5,
"แˆญ": 136,
"แˆฎ": 81,
"แˆฏ": 157,
"แˆฐ": 94,
"แˆฑ": 13,
"แˆฒ": 1,
"แˆณ": 2,
"แˆด": 208,
"แˆต": 191,
"แˆถ": 80,
"แˆท": 123,
"แˆธ": 175,
"แˆน": 34,
"แˆบ": 129,
"แˆป": 226,
"แˆผ": 223,
"แˆฝ": 187,
"แˆพ": 163,
"แ‰€": 198,
"แ‰": 90,
"แ‰‚": 35,
"แ‰ƒ": 207,
"แ‰„": 60,
"แ‰…": 173,
"แ‰†": 222,
"แ‰‹": 195,
"แ‰ ": 169,
"แ‰ก": 75,
"แ‰ข": 97,
"แ‰ฃ": 186,
"แ‰ค": 202,
"แ‰ฅ": 151,
"แ‰ฆ": 188,
"แ‰ง": 182,
"แ‰จ": 158,
"แ‰ช": 95,
"แ‰ซ": 36,
"แ‰ญ": 156,
"แ‰ฎ": 197,
"แ‰ฐ": 114,
"แ‰ฑ": 43,
"แ‰ฒ": 139,
"แ‰ณ": 23,
"แ‰ด": 105,
"แ‰ต": 138,
"แ‰ถ": 82,
"แ‰ท": 168,
"แ‰ธ": 108,
"แ‰น": 137,
"แ‰บ": 203,
"แ‰ป": 224,
"แ‰ผ": 183,
"แ‰ฝ": 225,
"แ‰พ": 210,
"แ‰ฟ": 51,
"แŠ€": 214,
"แŠƒ": 185,
"แŠ…": 11,
"แŠ‹": 130,
"แŠ": 177,
"แŠ‘": 204,
"แŠ’": 30,
"แŠ“": 49,
"แŠ”": 45,
"แŠ•": 14,
"แŠ–": 112,
"แŠ—": 145,
"แŠ˜": 70,
"แŠ™": 174,
"แŠ›": 64,
"แŠ": 59,
"แŠž": 38,
"แŠŸ": 180,
"แŠ ": 19,
"แŠก": 53,
"แŠข": 29,
"แŠค": 213,
"แŠฅ": 101,
"แŠฆ": 153,
"แŠจ": 221,
"แŠฉ": 91,
"แŠช": 17,
"แŠซ": 12,
"แŠฌ": 106,
"แŠญ": 190,
"แŠฎ": 72,
"แŠณ": 116,
"แŠธ": 84,
"แŠฝ": 132,
"แ‹ˆ": 85,
"แ‹Š": 122,
"แ‹‹": 50,
"แ‹Œ": 201,
"แ‹": 0,
"แ‹Ž": 121,
"แ‹": 73,
"แ‹‘": 155,
"แ‹’": 178,
"แ‹“": 26,
"แ‹•": 69,
"แ‹–": 152,
"แ‹˜": 118,
"แ‹™": 146,
"แ‹š": 76,
"แ‹›": 206,
"แ‹œ": 28,
"แ‹": 127,
"แ‹ž": 115,
"แ‹Ÿ": 104,
"แ‹ข": 83,
"แ‹ฃ": 219,
"แ‹ค": 125,
"แ‹ฅ": 140,
"แ‹ฆ": 99,
"แ‹จ": 57,
"แ‹ฉ": 62,
"แ‹ซ": 119,
"แ‹ฌ": 3,
"แ‹ญ": 211,
"แ‹ฎ": 33,
"แ‹ฐ": 74,
"แ‹ฑ": 96,
"แ‹ฒ": 67,
"แ‹ณ": 215,
"แ‹ด": 18,
"แ‹ต": 103,
"แ‹ถ": 10,
"แ‹ท": 154,
"แŒ€": 117,
"แŒ": 16,
"แŒ‚": 89,
"แŒƒ": 227,
"แŒ„": 61,
"แŒ…": 86,
"แŒ†": 181,
"แŒˆ": 39,
"แŒ‰": 113,
"แŒŠ": 161,
"แŒ‹": 52,
"แŒŒ": 196,
"แŒ": 66,
"แŒŽ": 217,
"แŒ“": 166,
"แŒ ": 41,
"แŒก": 143,
"แŒข": 205,
"แŒฃ": 209,
"แŒค": 4,
"แŒฅ": 160,
"แŒฆ": 93,
"แŒง": 193,
"แŒจ": 88,
"แŒฉ": 54,
"แŒช": 56,
"แŒซ": 199,
"แŒฌ": 162,
"แŒญ": 6,
"แŒฎ": 32,
"แŒฒ": 21,
"แŒด": 128,
"แŒต": 149,
"แŒถ": 68,
"แŒธ": 47,
"แŒน": 31,
"แŒบ": 179,
"แŒป": 98,
"แŒฝ": 37,
"แŒพ": 42,
"แŒฟ": 189,
"แ€": 65,
"แ": 100,
"แƒ": 216,
"แ…": 212,
"แˆ": 48,
"แ‰": 15,
"แŠ": 135,
"แ‹": 111,
"แŒ": 71,
"แ": 147,
"แŽ": 109,
"แ": 159,
"แ‘": 124,
"แ’": 25,
"แ“": 133,
"แ”": 131,
"แ•": 171,
"แ–": 92,
"โ€œ": 63,
"โ€": 20
}