swahili / vocab.json
etonkou's picture
Upload tokenizer
5017567
raw
history blame contribute delete
No virus
419 Bytes
{
"0": 22,
"1": 27,
"2": 9,
"3": 8,
"5": 33,
"6": 20,
"<": 2,
">": 34,
"[PAD]": 37,
"[UNK]": 36,
"_": 26,
"a": 10,
"b": 21,
"c": 18,
"d": 3,
"e": 5,
"f": 12,
"g": 35,
"h": 31,
"i": 4,
"j": 19,
"k": 14,
"l": 1,
"m": 28,
"n": 16,
"o": 7,
"p": 17,
"q": 29,
"r": 30,
"s": 23,
"t": 13,
"u": 6,
"v": 25,
"w": 32,
"x": 24,
"y": 15,
"z": 11,
"|": 0
}