bouim's picture
Upload tokenizer
220f7fa
raw
history blame contribute delete
466 Bytes
{
"[PAD]": 38,
"[UNK]": 37,
"|": 19,
"ء": 0,
"آ": 12,
"أ": 23,
"ؤ": 36,
"إ": 2,
"ئ": 33,
"ا": 10,
"ب": 27,
"ة": 16,
"ت": 24,
"ث": 22,
"ج": 35,
"ح": 6,
"خ": 20,
"د": 17,
"ذ": 8,
"ر": 29,
"ز": 21,
"س": 13,
"ش": 18,
"ص": 9,
"ض": 34,
"ط": 3,
"ظ": 14,
"ع": 5,
"غ": 26,
"ف": 32,
"ق": 30,
"ك": 1,
"ل": 31,
"م": 11,
"ن": 28,
"ه": 15,
"و": 4,
"ى": 25,
"ي": 7
}