ad019el's picture
Upload tokenizer
d58db91
raw
history blame
No virus
554 Bytes
{
"[PAD]": 47,
"[UNK]": 46,
"a": 31,
"b": 11,
"c": 36,
"d": 21,
"e": 28,
"f": 41,
"g": 30,
"h": 19,
"i": 5,
"j": 43,
"k": 40,
"l": 14,
"m": 37,
"n": 29,
"o": 25,
"p": 26,
"q": 8,
"r": 4,
"s": 0,
"t": 38,
"u": 12,
"v": 2,
"w": 20,
"x": 13,
"y": 9,
"z": 6,
"|": 33,
" ": 42,
"ĉ": 22,
"č": 17,
"ğ": 44,
"ţ": 32,
"ǧ": 7,
"ɛ": 18,
"ɣ": 1,
"̣": 27,
"γ": 10,
"ε": 3,
"ԑ": 34,
"چ": 35,
"ḍ": 16,
"ḥ": 45,
"ṛ": 15,
"ṣ": 23,
"ṭ": 39,
"ẓ": 24
}