Upload tokenizer
9b344fb
verified
|
{ |
|
"\n": 0, |
|
"$": 2, |
|
"&": 3, |
|
"(": 4, |
|
")": 5, |
|
"*": 6, |
|
"/": 7, |
|
"0": 8, |
|
"1": 9, |
|
"2": 10, |
|
"3": 11, |
|
"4": 12, |
|
"5": 13, |
|
"6": 14, |
|
"7": 15, |
|
"8": 16, |
|
"9": 17, |
|
"[PAD]": 66, |
|
"[UNK]": 65, |
|
"^": 18, |
|
"_": 19, |
|
"a": 20, |
|
"b": 21, |
|
"c": 22, |
|
"d": 23, |
|
"e": 24, |
|
"f": 25, |
|
"g": 26, |
|
"h": 27, |
|
"i": 28, |
|
"j": 29, |
|
"k": 30, |
|
"l": 31, |
|
"m": 32, |
|
"n": 33, |
|
"o": 34, |
|
"p": 35, |
|
"q": 36, |
|
"r": 37, |
|
"s": 38, |
|
"t": 39, |
|
"u": 40, |
|
"v": 41, |
|
"w": 42, |
|
"x": 43, |
|
"y": 44, |
|
"z": 45, |
|
"|": 1, |
|
"~": 46, |
|
"£": 47, |
|
"¨": 48, |
|
"µ": 49, |
|
"à": 50, |
|
"â": 51, |
|
"ç": 52, |
|
"è": 53, |
|
"é": 54, |
|
"ê": 55, |
|
"ë": 56, |
|
"ï": 57, |
|
"ñ": 58, |
|
"ó": 59, |
|
"ô": 60, |
|
"õ": 61, |
|
"ù": 62, |
|
"û": 63, |
|
"ŋ": 64 |
|
} |
|
|