Wiam's picture
add tokenizer
9836f42
{"ن": 0, "ا": 1, "ٌ": 2, "ل": 3, "ي": 4, "ؤ": 5, "ض": 6, "ص": 7, "ٍ": 8, "إ": 9, "ً": 10, "ی": 11, "أ": 12, "ة": 13, "ف": 14, "ذ": 15, "َ": 16, "غ": 17, "؟": 18, "ٰ": 19, "ج": 20, "ۖ": 21, "ش": 22, "،": 23, "آ": 24, "س": 25, "ث": 26, "ه": 27, "ى": 28, "ح": 29, "ك": 30, "ع": 31, "ّ": 32, "ْ": 33, "ئ": 34, "ت": 35, "ب": 36, "ر": 37, "ُ": 38, "ط": 39, "ز": 40, "ظ": 41, "د": 42, "م": 44, "ق": 45, "ـ": 46, "ء": 47, "ِ": 48, "و": 49, "خ": 50, "|": 43, "[UNK]": 51, "[PAD]": 52}