Lasion's picture
Upload tokenizer
7c1a3e1 verified
raw
history blame
1.17 kB
{
"[PAD]": 95,
"[UNK]": 94,
"a": 64,
"b": 38,
"c": 28,
"d": 29,
"e": 91,
"f": 92,
"g": 90,
"h": 20,
"i": 56,
"j": 15,
"k": 43,
"l": 76,
"m": 74,
"n": 55,
"o": 36,
"p": 68,
"q": 31,
"r": 67,
"s": 89,
"t": 75,
"u": 54,
"v": 73,
"w": 66,
"x": 49,
"y": 4,
"z": 58,
"|": 46,
"à": 2,
"á": 13,
"â": 48,
"ã": 63,
"è": 85,
"é": 9,
"ê": 57,
"ì": 50,
"í": 33,
"ò": 30,
"ó": 72,
"ô": 82,
"õ": 25,
"ù": 17,
"ú": 35,
"ý": 51,
"ă": 8,
"đ": 37,
"ĩ": 10,
"ũ": 22,
"ơ": 65,
"ư": 3,
"ạ": 84,
"ả": 93,
"ấ": 1,
"ầ": 47,
"ẩ": 61,
"ẫ": 81,
"ậ": 27,
"ắ": 88,
"ằ": 19,
"ẳ": 79,
"ẵ": 71,
"ặ": 40,
"ẹ": 32,
"ẻ": 14,
"ẽ": 45,
"ế": 59,
"ề": 41,
"ể": 52,
"ễ": 0,
"ệ": 62,
"ỉ": 83,
"ị": 34,
"ọ": 87,
"ỏ": 18,
"ố": 53,
"ồ": 24,
"ổ": 6,
"ỗ": 69,
"ộ": 70,
"ớ": 80,
"ờ": 5,
"ở": 16,
"ỡ": 11,
"ợ": 86,
"ụ": 12,
"ủ": 7,
"ứ": 26,
"ừ": 39,
"ử": 21,
"ữ": 77,
"ự": 23,
"ỳ": 78,
"ỵ": 44,
"ỷ": 42,
"ỹ": 60
}