Upload tokenizer
02339ba
verified
|
{ |
|
"&": 23, |
|
"'": 68, |
|
"(": 18, |
|
")": 104, |
|
"/": 15, |
|
"[PAD]": 111, |
|
"[UNK]": 110, |
|
"_": 52, |
|
"a": 76, |
|
"b": 29, |
|
"c": 48, |
|
"d": 8, |
|
"e": 86, |
|
"f": 62, |
|
"g": 39, |
|
"h": 100, |
|
"i": 84, |
|
"j": 98, |
|
"k": 0, |
|
"l": 20, |
|
"m": 67, |
|
"n": 92, |
|
"o": 82, |
|
"p": 106, |
|
"q": 55, |
|
"r": 59, |
|
"s": 9, |
|
"t": 99, |
|
"u": 81, |
|
"v": 46, |
|
"w": 89, |
|
"x": 108, |
|
"y": 2, |
|
"z": 33, |
|
"|": 19, |
|
"«": 56, |
|
"´": 32, |
|
"»": 25, |
|
"ß": 6, |
|
"à": 60, |
|
"á": 70, |
|
"â": 5, |
|
"ã": 75, |
|
"ä": 71, |
|
"å": 54, |
|
"æ": 26, |
|
"è": 77, |
|
"é": 17, |
|
"ê": 11, |
|
"ë": 30, |
|
"í": 65, |
|
"ï": 93, |
|
"ð": 38, |
|
"ñ": 83, |
|
"ò": 88, |
|
"ó": 97, |
|
"ô": 53, |
|
"ö": 16, |
|
"ø": 51, |
|
"ú": 90, |
|
"û": 74, |
|
"ü": 94, |
|
"ý": 49, |
|
"ā": 42, |
|
"ă": 7, |
|
"ą": 87, |
|
"ć": 44, |
|
"č": 40, |
|
"ď": 79, |
|
"đ": 14, |
|
"ę": 47, |
|
"ě": 73, |
|
"ğ": 1, |
|
"ī": 61, |
|
"ı": 107, |
|
"ł": 45, |
|
"ň": 105, |
|
"ō": 24, |
|
"ő": 96, |
|
"ř": 109, |
|
"ś": 22, |
|
"ş": 37, |
|
"š": 72, |
|
"ţ": 85, |
|
"ź": 13, |
|
"ž": 27, |
|
"ơ": 102, |
|
"ș": 103, |
|
"ț": 3, |
|
"ə": 64, |
|
"ʻ": 63, |
|
"ʿ": 21, |
|
"о": 69, |
|
"ѹ": 43, |
|
"ả": 50, |
|
"ắ": 36, |
|
"–": 12, |
|
"—": 95, |
|
"‘": 10, |
|
"’": 34, |
|
"‚": 101, |
|
"“": 35, |
|
"”": 41, |
|
"„": 58, |
|
"…": 4, |
|
"‹": 28, |
|
"›": 80, |
|
"乡": 31, |
|
"幺": 78, |
|
"無": 91, |
|
"生": 57, |
|
"辶": 66 |
|
} |
|
|