Reihaneh's picture
Upload tokenizer
c837dfc verified
raw
history blame contribute delete
No virus
645 Bytes
{
"'": 27,
"-": 47,
"F": 3,
"L": 24,
"N": 14,
"Y": 29,
"[": 0,
"[FY-NL]": 55,
"[NL]": 54,
"[PAD]": 53,
"[UNK]": 52,
"]": 8,
"a": 10,
"b": 40,
"c": 2,
"d": 11,
"e": 30,
"f": 48,
"g": 45,
"h": 25,
"i": 15,
"j": 38,
"k": 50,
"l": 43,
"m": 19,
"n": 21,
"o": 39,
"p": 42,
"q": 32,
"r": 28,
"s": 9,
"t": 23,
"u": 4,
"v": 26,
"w": 41,
"x": 33,
"y": 18,
"z": 49,
"|": 37,
"à": 20,
"á": 31,
"â": 5,
"ä": 6,
"è": 7,
"é": 34,
"ê": 12,
"ë": 35,
"ï": 36,
"ó": 13,
"ô": 16,
"ö": 17,
"ú": 51,
"û": 22,
"ü": 44,
"’": 46,
"…": 1
}