ms3c's picture
Upload tokenizer
bc3c677
raw
history blame contribute delete
488 Bytes
{
"\t": 0,
"\n": 1,
"0": 3,
"1": 4,
"2": 5,
"3": 6,
"4": 7,
"5": 8,
"6": 9,
"7": 10,
"8": 11,
"9": 12,
"[PAD]": 43,
"[UNK]": 42,
"_": 13,
"`": 14,
"a": 15,
"b": 16,
"c": 17,
"d": 18,
"e": 19,
"f": 20,
"g": 21,
"h": 22,
"i": 23,
"j": 24,
"k": 25,
"l": 26,
"m": 27,
"n": 28,
"o": 29,
"p": 30,
"q": 31,
"r": 32,
"s": 33,
"t": 34,
"u": 35,
"v": 36,
"w": 37,
"x": 38,
"y": 39,
"z": 40,
"|": 2,
"ū": 41
}