ayertey01's picture
Upload tokenizer
f4c7e35
raw
history blame
No virus
394 Bytes
{
"[PAD]": 34,
"[UNK]": 33,
"a": 19,
"b": 26,
"c": 27,
"d": 12,
"e": 8,
"f": 6,
"g": 2,
"h": 5,
"i": 32,
"j": 20,
"k": 10,
"l": 3,
"m": 25,
"n": 17,
"o": 1,
"p": 21,
"r": 14,
"s": 4,
"t": 7,
"u": 29,
"v": 13,
"w": 23,
"y": 22,
"z": 9,
"|": 16,
"á": 0,
"ã": 11,
"õ": 30,
"ĩ": 18,
"ũ": 15,
"ɔ": 24,
"ɛ": 28,
"́": 31
}