sanchit-gandhi's picture
Upload tokenizer
bc778b1
raw
history blame contribute delete
495 Bytes
{
" ": 44,
"'": 4,
"-": 23,
"0": 34,
"1": 36,
"2": 37,
"3": 41,
"4": 35,
"5": 38,
"6": 39,
"7": 40,
"a": 2,
"b": 20,
"c": 10,
"d": 25,
"e": 7,
"f": 31,
"g": 29,
"h": 11,
"i": 1,
"j": 8,
"k": 6,
"l": 14,
"m": 18,
"n": 5,
"o": 9,
"p": 22,
"q": 15,
"r": 3,
"s": 21,
"t": 13,
"u": 12,
"v": 32,
"w": 19,
"x": 16,
"y": 17,
"z": 24,
"|": 0,
"à": 42,
"á": 26,
"é": 30,
"ì": 43,
"í": 28,
"ó": 33,
"ú": 27
}