scarlett623's picture
Upload tokenizer
5c44501
raw
history blame
No virus
331 Bytes
{
"'": 3,
"[PAD]": 29,
"[UNK]": 28,
"a": 4,
"b": 27,
"c": 0,
"d": 12,
"e": 11,
"f": 21,
"g": 17,
"h": 14,
"i": 26,
"j": 10,
"k": 5,
"l": 20,
"m": 8,
"n": 15,
"o": 18,
"p": 7,
"q": 16,
"r": 13,
"s": 23,
"t": 24,
"u": 9,
"v": 6,
"w": 22,
"x": 1,
"y": 2,
"z": 19,
"|": 25
}