ad019el's picture
Upload tokenizer
5b57df5
raw
history blame
No virus
357 Bytes
{
"[PAD]": 31,
"[UNK]": 30,
"a": 18,
"b": 2,
"c": 0,
"d": 5,
"e": 26,
"f": 29,
"g": 27,
"h": 20,
"i": 15,
"j": 24,
"k": 16,
"l": 4,
"m": 23,
"n": 13,
"o": 17,
"p": 12,
"q": 28,
"r": 21,
"s": 3,
"t": 8,
"u": 11,
"v": 14,
"w": 7,
"x": 9,
"y": 10,
"z": 25,
"|": 22,
"ã": 1,
"ú": 6,
"ạ": 19
}