sulaimank's picture
Upload tokenizer
c0c1054 verified
raw
history blame
586 Bytes
{
"'": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"8": 9,
"9": 10,
"[PAD]": 51,
"[UNK]": 50,
"a": 11,
"b": 12,
"c": 13,
"d": 14,
"e": 15,
"f": 16,
"g": 17,
"h": 18,
"i": 19,
"j": 20,
"k": 21,
"l": 22,
"m": 23,
"n": 24,
"o": 25,
"p": 26,
"q": 27,
"r": 28,
"s": 29,
"t": 30,
"u": 31,
"v": 32,
"w": 33,
"x": 34,
"y": 35,
"z": 36,
"|": 0,
"á": 37,
"ã": 38,
"ç": 39,
"í": 40,
"ñ": 41,
"ó": 42,
"õ": 43,
"ú": 44,
"ü": 45,
"ŋ": 46,
"š": 47,
"η": 48,
"ղ": 49
}