Upload tokenizer
95e39dc
verified
|
{ |
|
"'": 1, |
|
"0": 2, |
|
"1": 3, |
|
"2": 4, |
|
"3": 5, |
|
"4": 6, |
|
"5": 7, |
|
"6": 8, |
|
"7": 9, |
|
"8": 10, |
|
"9": 11, |
|
"[PAD]": 67, |
|
"[UNK]": 66, |
|
"a": 12, |
|
"b": 13, |
|
"c": 14, |
|
"d": 15, |
|
"e": 16, |
|
"f": 17, |
|
"g": 18, |
|
"h": 19, |
|
"i": 20, |
|
"j": 21, |
|
"k": 22, |
|
"l": 23, |
|
"m": 24, |
|
"n": 25, |
|
"o": 26, |
|
"p": 27, |
|
"q": 28, |
|
"r": 29, |
|
"s": 30, |
|
"t": 31, |
|
"u": 32, |
|
"v": 33, |
|
"w": 34, |
|
"x": 35, |
|
"y": 36, |
|
"z": 37, |
|
"|": 0, |
|
"à": 38, |
|
"á": 39, |
|
"â": 40, |
|
"ã": 41, |
|
"å": 42, |
|
"ç": 43, |
|
"è": 44, |
|
"é": 45, |
|
"ë": 46, |
|
"í": 47, |
|
"ï": 48, |
|
"ñ": 49, |
|
"ó": 50, |
|
"ô": 51, |
|
"õ": 52, |
|
"ö": 53, |
|
"ø": 54, |
|
"ú": 55, |
|
"ü": 56, |
|
"š": 57, |
|
"ũ": 58, |
|
"ū": 59, |
|
"ː": 60, |
|
"μ": 61, |
|
"י": 62, |
|
"ạ": 63, |
|
"ọ": 64, |
|
"ụ": 65 |
|
} |
|
|