Rasooli's picture
Upload tokenizer
32e4324 verified
{
"#": 1,
"&": 2,
"(": 3,
")": 4,
"=": 5,
"[PAD]": 129,
"[UNK]": 128,
"_": 6,
"a": 7,
"b": 8,
"c": 9,
"d": 10,
"e": 11,
"f": 12,
"g": 13,
"h": 14,
"i": 15,
"k": 16,
"l": 17,
"m": 18,
"n": 19,
"o": 20,
"p": 21,
"q": 22,
"r": 23,
"s": 24,
"t": 25,
"u": 26,
"v": 27,
"w": 28,
"x": 29,
"y": 30,
"z": 31,
"|": 0,
"«": 32,
"»": 33,
"ā": 34,
"š": 35,
"،": 36,
"؛": 37,
"؟": 38,
"ء": 39,
"آ": 40,
"أ": 41,
"ؤ": 42,
"ئ": 43,
"ا": 44,
"ب": 45,
"ة": 46,
"ت": 47,
"ث": 48,
"ج": 49,
"ح": 50,
"خ": 51,
"د": 52,
"ذ": 53,
"ر": 54,
"ز": 55,
"س": 56,
"ش": 57,
"ص": 58,
"ض": 59,
"ط": 60,
"ظ": 61,
"ع": 62,
"غ": 63,
"ـ": 64,
"ف": 65,
"ق": 66,
"ك": 67,
"ل": 68,
"م": 69,
"ن": 70,
"ه": 71,
"و": 72,
"ى": 73,
"ي": 74,
"ً": 75,
"ٌ": 76,
"َ": 77,
"ُ": 78,
"ِ": 79,
"ّ": 80,
"ْ": 81,
"ٔ": 82,
"٬": 83,
"پ": 84,
"چ": 85,
"ژ": 86,
"ک": 87,
"گ": 88,
"ۀ": 89,
"ی": 90,
"ے": 91,
"ە": 92,
"–": 93,
"…": 94,
"ﭘ": 95,
"ﮐ": 96,
"ﮔ": 97,
"ﯽ": 98,
"ﯾ": 99,
"ﯿ": 100,
"ﺍ": 101,
"ﺎ": 102,
"ﺑ": 103,
"ﺒ": 104,
"ﺖ": 105,
"ﺘ": 106,
"ﺧ": 107,
"ﺩ": 108,
"ﺪ": 109,
"ﺭ": 110,
"ﺮ": 111,
"ﺱ": 112,
"ﺴ": 113,
"ﺷ": 114,
"ﺸ": 115,
"ﻀ": 116,
"ﻋ": 117,
"ﻌ": 118,
"ﻟ": 119,
"ﻡ": 120,
"ﻢ": 121,
"ﻤ": 122,
"ﻥ": 123,
"ﻧ": 124,
"ﻪ": 125,
"ﻭ": 126,
"ﻮ": 127
}