Hunzla's picture
Upload tokenizer
5bee8ed
raw
history blame
997 Bytes
{
",": 1,
"[PAD]": 81,
"[UNK]": 80,
"|": 0,
"ؑ": 2,
"ؓ": 3,
"ؔ": 4,
"ء": 5,
"آ": 6,
"أ": 7,
"ؤ": 8,
"ئ": 9,
"ا": 10,
"ب": 11,
"ت": 12,
"ث": 13,
"ج": 14,
"ح": 15,
"خ": 16,
"د": 17,
"ذ": 18,
"ر": 19,
"ز": 20,
"س": 21,
"ش": 22,
"ص": 23,
"ض": 24,
"ط": 25,
"ظ": 26,
"ع": 27,
"غ": 28,
"ف": 29,
"ق": 30,
"ك": 31,
"ل": 32,
"م": 33,
"ن": 34,
"ه": 35,
"و": 36,
"ى": 37,
"ً": 38,
"َ": 39,
"ُ": 40,
"ِ": 41,
"ّ": 42,
"ْ": 43,
"ٓ": 44,
"ٔ": 45,
"ٗ": 46,
"ٰ": 47,
"ٹ": 48,
"پ": 49,
"چ": 50,
"ڈ": 51,
"ڑ": 52,
"ژ": 53,
"ک": 54,
"گ": 55,
"ں": 56,
"ھ": 57,
"ہ": 58,
"ۂ": 59,
"ۃ": 60,
"ی": 61,
"ے": 62,
"ۓ": 63,
"‘": 64,
"’": 65,
"“": 66,
"”": 67,
"…": 68,
"ﭨ": 69,
"ﮭ": 70,
"ﮯ": 71,
"ﯾ": 72,
"ﷲ": 73,
"ﷺ": 74,
"ﺘ": 75,
"ﺩ": 76,
"ﺲ": 77,
"ﻧ": 78,
"ﻮ": 79
}