mms-en / vocab.json
akera's picture
Upload tokenizer
1d7c419
raw history blame
No virus
519 Bytes
{
"en": {
">": 1,
"[PAD]": 37,
"[UNK]": 36,
"`": 2,
"a": 3,
"b": 4,
"c": 5,
"d": 6,
"e": 7,
"f": 8,
"g": 9,
"h": 10,
"i": 11,
"j": 12,
"k": 13,
"l": 14,
"m": 15,
"n": 16,
"o": 17,
"p": 18,
"q": 19,
"r": 20,
"s": 21,
"t": 22,
"u": 23,
"v": 24,
"w": 25,
"x": 26,
"y": 27,
"z": 28,
"|": 0,
"´": 29,
"ä": 30,
"é": 31,
"ô": 32,
"‚": 33,
"“": 34,
"”": 35
}
}