St4n's picture
Upload tokenizer
d7480c5 verified
raw
history blame
No virus
309 Bytes
{
"[PAD]": 27,
"[UNK]": 26,
"a": 20,
"b": 4,
"c": 24,
"d": 6,
"e": 7,
"f": 17,
"g": 8,
"h": 25,
"i": 22,
"k": 21,
"l": 14,
"m": 19,
"n": 1,
"o": 10,
"p": 2,
"q": 16,
"r": 23,
"s": 9,
"t": 3,
"u": 0,
"v": 18,
"w": 11,
"x": 5,
"y": 12,
"z": 15,
"|": 13
}