Reihaneh's picture
Upload tokenizer
ce4ae9a verified
raw
history blame
No virus
488 Bytes
{
"'": 39,
"[PAD]": 42,
"[UNK]": 41,
"a": 36,
"b": 22,
"c": 28,
"d": 37,
"e": 18,
"f": 21,
"g": 26,
"h": 8,
"i": 24,
"j": 27,
"k": 11,
"l": 31,
"m": 5,
"n": 2,
"o": 23,
"p": 6,
"q": 7,
"r": 15,
"s": 12,
"t": 19,
"u": 4,
"v": 13,
"w": 29,
"x": 14,
"y": 34,
"z": 1,
"|": 38,
"à": 20,
"á": 17,
"â": 9,
"ä": 30,
"é": 35,
"ê": 3,
"ë": 33,
"ï": 0,
"ô": 32,
"ú": 10,
"û": 25,
"ü": 40,
"‘": 16
}