ad019el's picture
Upload tokenizer
7f256c2
raw
history blame
478 Bytes
{
"[PAD]": 39,
"[UNK]": 38,
"|": 36,
"ء": 16,
"آ": 5,
"أ": 1,
"إ": 28,
"ئ": 27,
"ا": 22,
"ب": 35,
"ة": 14,
"ت": 19,
"ث": 26,
"ج": 17,
"ح": 13,
"خ": 33,
"د": 8,
"ذ": 18,
"ر": 2,
"ز": 30,
"س": 0,
"ش": 20,
"ص": 10,
"ض": 31,
"ط": 15,
"ظ": 32,
"ع": 4,
"غ": 6,
"ف": 3,
"ق": 29,
"ك": 7,
"ل": 24,
"م": 37,
"ن": 12,
"ه": 9,
"و": 21,
"ى": 34,
"ي": 23,
"ٱ": 11,
"ڤ": 25
}