large_base_M07 / vocab.json
mprzibilla's picture
Upload tokenizer
c34d3e6
raw
history blame
309 Bytes
{
"[PAD]": 27,
"[UNK]": 26,
"a": 5,
"b": 17,
"c": 14,
"d": 25,
"e": 15,
"f": 3,
"g": 9,
"h": 24,
"i": 1,
"j": 13,
"k": 21,
"l": 8,
"m": 20,
"n": 18,
"o": 0,
"p": 10,
"q": 16,
"r": 6,
"s": 11,
"t": 12,
"u": 2,
"v": 7,
"w": 22,
"x": 4,
"y": 19,
"|": 23
}