sulaimank's picture
Upload tokenizer
bdc15fd verified
raw
history blame
525 Bytes
{
"'": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"7": 9,
"8": 10,
"9": 11,
"[PAD]": 46,
"[UNK]": 45,
"a": 12,
"b": 13,
"c": 14,
"d": 15,
"e": 16,
"f": 17,
"g": 18,
"h": 19,
"i": 20,
"j": 21,
"k": 22,
"l": 23,
"m": 24,
"n": 25,
"o": 26,
"p": 27,
"q": 28,
"r": 29,
"s": 30,
"t": 31,
"u": 32,
"v": 33,
"w": 34,
"x": 35,
"y": 36,
"z": 37,
"|": 0,
"á": 38,
"â": 39,
"ç": 40,
"í": 41,
"ô": 42,
"õ": 43,
"ü": 44
}