alanrice's picture
Upload tokenizer
b37ef1f
raw
history blame
417 Bytes
{
"(": 1,
")": 2,
"*": 3,
"[PAD]": 36,
"[UNK]": 35,
"a": 4,
"b": 5,
"c": 6,
"d": 7,
"e": 8,
"f": 9,
"g": 10,
"h": 11,
"i": 12,
"j": 13,
"k": 14,
"l": 15,
"m": 16,
"n": 17,
"o": 18,
"p": 19,
"r": 20,
"s": 21,
"t": 22,
"u": 23,
"v": 24,
"w": 25,
"x": 26,
"y": 27,
"|": 0,
"á": 28,
"é": 29,
"í": 30,
"ó": 31,
"ú": 32,
"–": 33,
"’": 34
}