paruwka's picture
Upload tokenizer
1e4d23c verified
raw history blame
No virus
1.06 kB
{
"&": 34,
"'": 58,
"(": 56,
")": 62,
"=": 22,
"[PAD]": 89,
"[UNK]": 88,
"a": 21,
"b": 50,
"c": 59,
"d": 15,
"e": 36,
"f": 71,
"g": 5,
"h": 75,
"i": 23,
"j": 29,
"k": 82,
"l": 83,
"m": 16,
"n": 37,
"o": 9,
"p": 44,
"q": 80,
"r": 3,
"s": 14,
"t": 66,
"u": 27,
"v": 52,
"w": 4,
"x": 41,
"y": 12,
"z": 72,
"|": 53,
"«": 6,
"´": 31,
"»": 1,
"ß": 74,
"à": 13,
"á": 26,
"â": 79,
"ã": 64,
"ä": 54,
"å": 48,
"æ": 8,
"ç": 10,
"è": 63,
"é": 20,
"ê": 60,
"ë": 65,
"ì": 32,
"î": 78,
"ï": 30,
"ð": 76,
"ñ": 7,
"ó": 61,
"ô": 25,
"ö": 0,
"ø": 40,
"ù": 33,
"ú": 81,
"û": 69,
"ü": 84,
"þ": 43,
"ÿ": 24,
"ă": 18,
"ć": 28,
"č": 47,
"ē": 57,
"ğ": 39,
"ō": 49,
"œ": 46,
"ş": 86,
"š": 73,
"ū": 19,
"ž": 51,
"ș": 17,
"ʻ": 70,
"̀": 68,
"́": 87,
"̂": 11,
"̧": 77,
"–": 67,
"—": 42,
"’": 38,
"“": 35,
"”": 55,
"…": 2,
"の": 85,
"ひ": 45
}