Anujgr8's picture
Upload tokenizer
20f0dda verified
{
"\t": 0,
"\n": 1,
"!": 3,
"\"": 4,
"%": 5,
"'": 6,
",": 7,
"-": 8,
".": 9,
"/": 10,
"0": 11,
"1": 12,
"2": 13,
"3": 14,
"4": 15,
"5": 16,
"6": 17,
"7": 18,
"8": 19,
"9": 20,
":": 21,
";": 22,
"?": 23,
"B": 24,
"F": 25,
"H": 26,
"K": 27,
"L": 28,
"O": 29,
"T": 30,
"[PAD]": 146,
"[UNK]": 145,
"_": 31,
"a": 32,
"b": 33,
"c": 34,
"d": 35,
"e": 36,
"f": 37,
"g": 38,
"h": 39,
"i": 40,
"j": 41,
"k": 42,
"l": 43,
"m": 44,
"n": 45,
"o": 46,
"p": 47,
"r": 48,
"s": 49,
"t": 50,
"u": 51,
"v": 52,
"w": 53,
"x": 54,
"y": 55,
"z": 56,
"|": 2,
"“": 57,
"”": 58,
"œ": 59,
"।": 60,
"ঁ": 61,
"ং": 62,
"ঃ": 63,
"অ": 64,
"আ": 65,
"ই": 66,
"ঈ": 67,
"উ": 68,
"ঊ": 69,
"ঋ": 70,
"এ": 71,
"ঐ": 72,
"ও": 73,
"ঔ": 74,
"ক": 75,
"খ": 76,
"গ": 77,
"ঘ": 78,
"ঙ": 79,
"চ": 80,
"ছ": 81,
"জ": 82,
"ঝ": 83,
"ঞ": 84,
"ট": 85,
"ঠ": 86,
"ড": 87,
"ঢ": 88,
"ণ": 89,
"ত": 90,
"থ": 91,
"দ": 92,
"ধ": 93,
"ন": 94,
"প": 95,
"ফ": 96,
"ব": 97,
"ভ": 98,
"ম": 99,
"য": 100,
"র": 101,
"ল": 102,
"শ": 103,
"ষ": 104,
"স": 105,
"হ": 106,
"়": 107,
"া": 108,
"ি": 109,
"ী": 110,
"ু": 111,
"ূ": 112,
"ৃ": 113,
"ে": 114,
"ৈ": 115,
"ো": 116,
"ৌ": 117,
"্": 118,
"ৎ": 119,
"ৗ": 120,
"ড়": 121,
"ঢ়": 122,
"য়": 123,
"০": 124,
"১": 125,
"২": 126,
"৩": 127,
"৪": 128,
"৫": 129,
"৬": 130,
"৭": 131,
"৮": 132,
"৯": 133,
"ৰ": 134,
"‌": 135,
"‍": 136,
"‎": 137,
"–": 138,
"—": 139,
"‘": 140,
"’": 141,
"“": 142,
"”": 143,
"…": 144
}