khaoulaoub's picture
Upload tokenizer
2b37b60
raw
history blame
No virus
406 Bytes
{
"[PAD]": 33,
"[UNK]": 32,
"|": 2,
"ء": 27,
"ا": 7,
"ب": 20,
"ة": 22,
"ت": 30,
"ث": 23,
"ج": 1,
"ح": 24,
"خ": 13,
"د": 19,
"ذ": 8,
"ر": 18,
"ز": 12,
"س": 16,
"ش": 28,
"ص": 11,
"ض": 4,
"ط": 14,
"ظ": 21,
"ع": 25,
"غ": 29,
"ف": 17,
"ق": 6,
"ك": 15,
"ل": 5,
"م": 3,
"ن": 9,
"ه": 0,
"و": 31,
"ى": 26,
"ي": 10
}