federicocosta1989's picture
Upload tokenizer
c04a43d verified
raw
history blame
No virus
279 Bytes
{
"[PAD]": 24,
"[UNK]": 23,
"a": 21,
"b": 2,
"d": 3,
"e": 16,
"g": 5,
"h": 15,
"i": 10,
"j": 4,
"k": 22,
"l": 12,
"m": 18,
"n": 0,
"o": 9,
"p": 6,
"s": 1,
"t": 8,
"u": 19,
"w": 20,
"y": 13,
"|": 7,
"é": 11,
"ñ": 17,
"ô": 14
}