large_base_M14 / vocab.json
mprzibilla's picture
Upload tokenizer
6271eea
raw
history blame
309 Bytes
{
"[PAD]": 27,
"[UNK]": 26,
"a": 5,
"b": 7,
"c": 12,
"d": 2,
"e": 20,
"f": 23,
"g": 19,
"h": 22,
"i": 24,
"j": 10,
"k": 4,
"l": 15,
"m": 18,
"n": 1,
"o": 13,
"p": 0,
"q": 21,
"r": 16,
"s": 6,
"t": 14,
"u": 25,
"v": 8,
"w": 9,
"y": 17,
"z": 3,
"|": 11
}