Samuael's picture
Upload tokenizer
125148c verified
raw
history blame contribute delete
No virus
3.16 kB
{
"[PAD]": 0,
"[UNK]": 1,
"|": 2,
"แˆ": 39,
"แˆ‚": 40,
"แˆ„": 41,
"แˆ…": 3,
"แˆ†": 42,
"แˆˆ": 43,
"แˆ‰": 44,
"แˆŠ": 45,
"แˆ‹": 46,
"แˆŒ": 47,
"แˆ": 4,
"แˆŽ": 48,
"แˆ": 201,
"แˆ": 38,
"แˆ—": 200,
"แˆ˜": 49,
"แˆ™": 50,
"แˆš": 51,
"แˆ›": 52,
"แˆœ": 53,
"แˆ": 5,
"แˆž": 54,
"แˆŸ": 202,
"แˆจ": 55,
"แˆฉ": 56,
"แˆช": 57,
"แˆซ": 58,
"แˆฌ": 59,
"แˆญ": 6,
"แˆฎ": 60,
"แˆฏ": 203,
"แˆฐ": 61,
"แˆฑ": 62,
"แˆฒ": 63,
"แˆณ": 64,
"แˆด": 65,
"แˆต": 7,
"แˆถ": 66,
"แˆท": 204,
"แˆธ": 67,
"แˆน": 68,
"แˆบ": 69,
"แˆป": 70,
"แˆผ": 71,
"แˆฝ": 8,
"แˆพ": 72,
"แˆฟ": 205,
"แ‰€": 73,
"แ‰": 74,
"แ‰‚": 75,
"แ‰ƒ": 76,
"แ‰„": 77,
"แ‰…": 9,
"แ‰†": 78,
"แ‰Š": 232,
"แ‰‹": 206,
"แ‰Œ": 228,
"แ‰ ": 79,
"แ‰ก": 80,
"แ‰ข": 81,
"แ‰ฃ": 82,
"แ‰ค": 83,
"แ‰ฅ": 10,
"แ‰ฆ": 84,
"แ‰ง": 207,
"แ‰จ": 85,
"แ‰ฉ": 86,
"แ‰ช": 87,
"แ‰ซ": 88,
"แ‰ฌ": 89,
"แ‰ญ": 11,
"แ‰ฎ": 90,
"แ‰ฏ": 208,
"แ‰ฐ": 91,
"แ‰ฑ": 92,
"แ‰ฒ": 93,
"แ‰ณ": 94,
"แ‰ด": 95,
"แ‰ต": 12,
"แ‰ถ": 96,
"แ‰ท": 209,
"แ‰ธ": 97,
"แ‰น": 98,
"แ‰บ": 99,
"แ‰ป": 100,
"แ‰ผ": 101,
"แ‰ฝ": 13,
"แ‰พ": 102,
"แ‰ฟ": 210,
"แŠŠ": 231,
"แŠŒ": 227,
"แŠ": 103,
"แŠ‘": 104,
"แŠ’": 105,
"แŠ“": 106,
"แŠ”": 107,
"แŠ•": 14,
"แŠ–": 108,
"แŠ—": 211,
"แŠ˜": 109,
"แŠ™": 110,
"แŠš": 111,
"แŠ›": 112,
"แŠœ": 113,
"แŠ": 15,
"แŠž": 114,
"แŠŸ": 212,
"แŠ ": 31,
"แŠก": 32,
"แŠข": 33,
"แŠค": 34,
"แŠฅ": 35,
"แŠฆ": 36,
"แŠง": 30,
"แŠจ": 115,
"แŠฉ": 116,
"แŠช": 117,
"แŠซ": 118,
"แŠฌ": 119,
"แŠญ": 16,
"แŠฎ": 120,
"แŠฐ": 121,
"แŠฒ": 230,
"แŠณ": 213,
"แŠด": 226,
"แŠธ": 37,
"แ‹ˆ": 122,
"แ‹‰": 123,
"แ‹Š": 124,
"แ‹‹": 125,
"แ‹Œ": 126,
"แ‹": 17,
"แ‹Ž": 127,
"แ‹˜": 128,
"แ‹™": 129,
"แ‹š": 130,
"แ‹›": 131,
"แ‹œ": 132,
"แ‹": 18,
"แ‹ž": 133,
"แ‹Ÿ": 214,
"แ‹ ": 134,
"แ‹ก": 135,
"แ‹ข": 136,
"แ‹ฃ": 137,
"แ‹ค": 138,
"แ‹ฅ": 19,
"แ‹ฆ": 139,
"แ‹ง": 215,
"แ‹จ": 140,
"แ‹ฉ": 141,
"แ‹ช": 142,
"แ‹ซ": 143,
"แ‹ฌ": 144,
"แ‹ญ": 20,
"แ‹ฎ": 145,
"แ‹ฐ": 146,
"แ‹ฑ": 147,
"แ‹ฒ": 148,
"แ‹ณ": 149,
"แ‹ด": 150,
"แ‹ต": 21,
"แ‹ถ": 151,
"แ‹ท": 216,
"แŒ€": 152,
"แŒ": 153,
"แŒ‚": 154,
"แŒƒ": 155,
"แŒ„": 156,
"แŒ…": 22,
"แŒ†": 157,
"แŒ‡": 217,
"แŒˆ": 158,
"แŒ‰": 159,
"แŒŠ": 160,
"แŒ‹": 161,
"แŒŒ": 162,
"แŒ": 23,
"แŒ": 163,
"แŒ’": 229,
"แŒ“": 218,
"แŒ”": 225,
"แŒ ": 164,
"แŒก": 165,
"แŒข": 166,
"แŒฃ": 167,
"แŒค": 168,
"แŒฅ": 24,
"แŒฆ": 169,
"แŒง": 219,
"แŒจ": 170,
"แŒฉ": 171,
"แŒช": 172,
"แŒซ": 173,
"แŒฌ": 174,
"แŒญ": 25,
"แŒฎ": 175,
"แŒฏ": 220,
"แŒฐ": 176,
"แŒฑ": 177,
"แŒฒ": 178,
"แŒณ": 179,
"แŒด": 180,
"แŒต": 26,
"แŒถ": 181,
"แŒท": 221,
"แŒธ": 182,
"แŒน": 183,
"แŒบ": 184,
"แŒป": 185,
"แŒผ": 186,
"แŒฝ": 27,
"แŒพ": 187,
"แŒฟ": 222,
"แˆ": 188,
"แ‰": 189,
"แŠ": 190,
"แ‹": 191,
"แŒ": 192,
"แ": 28,
"แŽ": 193,
"แ": 223,
"แ": 194,
"แ‘": 195,
"แ’": 196,
"แ“": 197,
"แ”": 198,
"แ•": 29,
"แ–": 199,
"แ—": 224
}