sanchit-gandhi's picture
add tokenizer
a076edc
{
"'": 12,
"-": 8,
"1": 23,
"</s>": 2,
"<pad>": 0,
"<s>": 1,
"<unk>": 3,
"a": 22,
"b": 20,
"c": 5,
"d": 25,
"e": 15,
"f": 29,
"g": 14,
"h": 24,
"i": 26,
"j": 33,
"k": 19,
"l": 7,
"m": 30,
"n": 13,
"o": 6,
"p": 10,
"q": 31,
"r": 9,
"s": 11,
"t": 4,
"u": 28,
"v": 16,
"w": 17,
"x": 32,
"y": 21,
"z": 18,
"|": 27
}