tirtho-finetuned / vocab.json
Tirthankar's picture
Upload tokenizer
daf1741
raw
history blame contribute delete
890 Bytes
{
"</s>": 4,
"<s>": 3,
"[PAD]": 0,
"[UNK]": 1,
"|": 2,
"،": 11,
"؟": 16,
"ؠ": 73,
"آ": 33,
"أ": 42,
"ؤ": 22,
"إ": 31,
"ا": 59,
"ب": 71,
"ت": 47,
"ث": 46,
"ج": 53,
"ح": 49,
"خ": 65,
"د": 23,
"ذ": 36,
"ر": 39,
"ز": 58,
"س": 32,
"ش": 24,
"ص": 63,
"ض": 27,
"ط": 61,
"ظ": 6,
"ع": 44,
"غ": 35,
"ف": 41,
"ق": 68,
"ل": 38,
"م": 17,
"ن": 60,
"و": 28,
"ً": 30,
"َ": 54,
"ُ": 18,
"ِ": 70,
"ّ": 19,
"ْ": 10,
"ٓ": 66,
"ٔ": 7,
"ٕ": 21,
"ٖ": 8,
"ٗ": 29,
"ٚ": 72,
"ٟ": 15,
"ٮ": 62,
"ٲ": 64,
"ٹ": 14,
"پ": 5,
"چ": 57,
"ڈ": 69,
"ڑ": 55,
"ژ": 20,
"ک": 34,
"گ": 48,
"ں": 52,
"ھ": 50,
"ہ": 40,
"ۄ": 43,
"ۆ": 37,
"ی": 25,
"ے": 9,
"۔": 12,
"۱": 26,
"۵": 51,
"۷": 45,
"۸": 67,
"۹": 56,
"“": 13
}