FarhadMadadzade's picture
Upload tokenizer
74a11cb verified
raw
history blame
369 Bytes
{
"'": 5,
"-": 6,
"</s>": 2,
"<pad>": 0,
"<s>": 1,
"<unk>": 3,
"a": 7,
"b": 8,
"c": 9,
"d": 10,
"e": 11,
"f": 12,
"g": 13,
"h": 14,
"i": 15,
"j": 16,
"k": 17,
"l": 18,
"m": 19,
"n": 20,
"o": 21,
"p": 22,
"q": 23,
"r": 24,
"s": 25,
"t": 26,
"u": 27,
"v": 28,
"w": 29,
"x": 30,
"y": 31,
"z": 32,
"|": 4
}