paruwka's picture
Upload tokenizer
bbf2aa6 verified
raw
history blame
No virus
786 Bytes
{
"&": 12,
"'": 39,
"(": 19,
")": 8,
"=": 46,
"[PAD]": 67,
"[UNK]": 66,
"a": 36,
"b": 6,
"c": 16,
"d": 50,
"e": 41,
"f": 44,
"g": 10,
"h": 4,
"i": 15,
"j": 2,
"k": 11,
"l": 28,
"m": 25,
"n": 55,
"o": 48,
"p": 21,
"q": 5,
"r": 49,
"s": 29,
"t": 22,
"u": 52,
"v": 57,
"w": 32,
"x": 31,
"y": 37,
"z": 33,
"|": 17,
"«": 20,
"»": 56,
"ß": 42,
"à": 26,
"á": 40,
"â": 47,
"ç": 27,
"è": 3,
"é": 23,
"ê": 34,
"ë": 64,
"î": 30,
"ï": 60,
"ó": 51,
"ô": 7,
"ö": 54,
"ø": 14,
"ù": 65,
"ú": 62,
"û": 61,
"ü": 53,
"ć": 43,
"ē": 63,
"ō": 38,
"œ": 18,
"š": 59,
"ū": 13,
"̀": 1,
"́": 45,
"̂": 9,
"̧": 58,
"—": 24,
"’": 35,
"…": 0
}