nathanhunt's picture
Upload tokenizer
700265b
raw
history blame
738 Bytes
{
"$": 1,
"&": 2,
"+": 3,
"/": 4,
"0": 5,
"1": 6,
"2": 7,
"3": 8,
"4": 9,
"5": 10,
"6": 11,
"7": 12,
"8": 13,
"9": 14,
"[": 15,
"[PAD]": 64,
"[UNK]": 63,
"]": 16,
"a": 17,
"b": 18,
"c": 19,
"d": 20,
"e": 21,
"f": 22,
"g": 23,
"h": 24,
"i": 25,
"j": 26,
"k": 27,
"l": 28,
"m": 29,
"n": 30,
"o": 31,
"p": 32,
"q": 33,
"r": 34,
"s": 35,
"t": 36,
"u": 37,
"v": 38,
"w": 39,
"x": 40,
"y": 41,
"z": 42,
"|": 0,
"~": 43,
"¥": 44,
"²": 45,
"á": 46,
"ã": 47,
"ç": 48,
"é": 49,
"í": 50,
"ó": 51,
"õ": 52,
"ö": 53,
"ú": 54,
"ü": 55,
"ă": 56,
"ğ": 57,
"ş": 58,
"ŵ": 59,
"’": 60,
"⁰": 61,
"◦": 62
}