batoula187's picture
Upload tokenizer
010408b verified
raw
history blame
No virus
1.13 kB
{
"(": 1,
")": 2,
"[PAD]": 95,
"[UNK]": 94,
"_": 3,
"a": 4,
"b": 5,
"c": 6,
"d": 7,
"e": 8,
"f": 9,
"g": 10,
"h": 11,
"i": 12,
"j": 13,
"k": 14,
"l": 15,
"m": 16,
"n": 17,
"o": 18,
"p": 19,
"q": 20,
"r": 21,
"s": 22,
"t": 23,
"u": 24,
"v": 25,
"w": 26,
"x": 27,
"y": 28,
"|": 0,
"«": 29,
"»": 30,
"،": 31,
"؛": 32,
"؟": 33,
"ء": 34,
"آ": 35,
"أ": 36,
"ؤ": 37,
"إ": 38,
"ئ": 39,
"ا": 40,
"ب": 41,
"ة": 42,
"ت": 43,
"ث": 44,
"ج": 45,
"ح": 46,
"خ": 47,
"د": 48,
"ذ": 49,
"ر": 50,
"ز": 51,
"س": 52,
"ش": 53,
"ص": 54,
"ض": 55,
"ط": 56,
"ظ": 57,
"ع": 58,
"غ": 59,
"ـ": 60,
"ف": 61,
"ق": 62,
"ك": 63,
"ل": 64,
"م": 65,
"ن": 66,
"ه": 67,
"و": 68,
"ى": 69,
"ي": 70,
"ً": 71,
"ٌ": 72,
"ٍ": 73,
"َ": 74,
"ُ": 75,
"ِ": 76,
"ّ": 77,
"ْ": 78,
"ٰ": 79,
"چ": 80,
"ڨ": 81,
"ک": 82,
"ھ": 83,
"ی": 84,
"ۖ": 85,
"ۗ": 86,
"ۘ": 87,
"ۚ": 88,
"ۛ": 89,
"—": 90,
"☭": 91,
"ﺃ": 92,
"ﻻ": 93
}