rms7988's picture
Upload tokenizer
cc586aa verified
raw
history blame
No virus
427 Bytes
{
"'": 24,
"[PAD]": 37,
"[UNK]": 36,
"a": 0,
"b": 27,
"c": 15,
"d": 5,
"e": 17,
"f": 26,
"g": 11,
"h": 35,
"i": 3,
"j": 9,
"k": 7,
"l": 12,
"m": 21,
"n": 10,
"o": 13,
"p": 16,
"q": 1,
"r": 8,
"s": 22,
"t": 23,
"u": 30,
"v": 34,
"w": 33,
"x": 18,
"y": 14,
"z": 6,
"|": 32,
"à": 20,
"á": 2,
"è": 29,
"é": 19,
"í": 28,
"ñ": 4,
"ö": 25,
"ō": 31
}