ALIGHASEMI931's picture
Upload tokenizer
8a8474f
raw
history blame
1.52 kB
{
"#": 1,
"&": 2,
"(": 3,
")": 4,
"[PAD]": 123,
"[UNK]": 122,
"_": 5,
"a": 6,
"b": 7,
"c": 8,
"d": 9,
"e": 10,
"f": 11,
"g": 12,
"h": 13,
"i": 14,
"k": 15,
"m": 16,
"n": 17,
"o": 18,
"p": 19,
"q": 20,
"r": 21,
"s": 22,
"t": 23,
"u": 24,
"y": 25,
"z": 26,
"|": 0,
"«": 27,
"»": 28,
"ā": 29,
"š": 30,
"،": 31,
"؛": 32,
"؟": 33,
"ء": 34,
"آ": 35,
"أ": 36,
"ؤ": 37,
"ئ": 38,
"ا": 39,
"ب": 40,
"ة": 41,
"ت": 42,
"ث": 43,
"ج": 44,
"ح": 45,
"خ": 46,
"د": 47,
"ذ": 48,
"ر": 49,
"ز": 50,
"س": 51,
"ش": 52,
"ص": 53,
"ض": 54,
"ط": 55,
"ظ": 56,
"ع": 57,
"غ": 58,
"ـ": 59,
"ف": 60,
"ق": 61,
"ك": 62,
"ل": 63,
"م": 64,
"ن": 65,
"ه": 66,
"و": 67,
"ى": 68,
"ي": 69,
"ً": 70,
"ٌ": 71,
"َ": 72,
"ُ": 73,
"ِ": 74,
"ّ": 75,
"ْ": 76,
"ٔ": 77,
"٬": 78,
"پ": 79,
"چ": 80,
"ژ": 81,
"ک": 82,
"گ": 83,
"ۀ": 84,
"ی": 85,
"ے": 86,
"–": 87,
"…": 88,
"ﭘ": 89,
"ﮐ": 90,
"ﮔ": 91,
"ﯽ": 92,
"ﯾ": 93,
"ﯿ": 94,
"ﺍ": 95,
"ﺎ": 96,
"ﺑ": 97,
"ﺒ": 98,
"ﺖ": 99,
"ﺘ": 100,
"ﺧ": 101,
"ﺩ": 102,
"ﺪ": 103,
"ﺭ": 104,
"ﺮ": 105,
"ﺱ": 106,
"ﺴ": 107,
"ﺷ": 108,
"ﺸ": 109,
"ﻀ": 110,
"ﻋ": 111,
"ﻌ": 112,
"ﻟ": 113,
"ﻡ": 114,
"ﻢ": 115,
"ﻤ": 116,
"ﻥ": 117,
"ﻧ": 118,
"ﻪ": 119,
"ﻭ": 120,
"ﻮ": 121
}