sulaimank's picture
Upload tokenizer
165c4a4 verified
raw
history blame contribute delete
354 Bytes
{
"'": 1,
"1": 2,
"9": 3,
"[PAD]": 31,
"[UNK]": 30,
"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,
"q": 20,
"r": 21,
"s": 22,
"t": 23,
"u": 24,
"v": 25,
"w": 26,
"y": 27,
"z": 28,
"|": 0,
"ŋ": 29
}