samuelchiji's picture
Upload tokenizer
5a50225 verified
raw history blame
No virus
357 Bytes
{
"2": 17,
"[PAD]": 31,
"[UNK]": 30,
"a": 27,
"b": 1,
"c": 29,
"d": 16,
"e": 8,
"f": 19,
"g": 21,
"h": 9,
"i": 0,
"j": 4,
"k": 13,
"l": 12,
"m": 3,
"n": 15,
"o": 7,
"p": 11,
"q": 28,
"r": 6,
"s": 26,
"t": 20,
"u": 10,
"v": 22,
"w": 23,
"x": 25,
"y": 24,
"z": 14,
"|": 5,
"ẹ": 18,
"’": 2
}