sanchit-gandhi's picture
add tokenizer
e9bf05f
{
"'": 29,
"-": 25,
"1": 18,
"</s>": 2,
"<pad>": 0,
"<s>": 1,
"<unk>": 3,
"a": 23,
"b": 33,
"c": 22,
"d": 21,
"e": 14,
"f": 11,
"g": 6,
"h": 9,
"i": 26,
"j": 4,
"k": 15,
"l": 17,
"m": 8,
"n": 30,
"o": 20,
"p": 19,
"q": 12,
"r": 13,
"s": 10,
"t": 24,
"u": 7,
"v": 31,
"w": 32,
"x": 28,
"y": 16,
"z": 27,
"|": 5
}