Thienpkae's picture
Upload tokenizer
1ea9725 verified
raw
history blame
No virus
1.13 kB
{
"A": 1,
"B": 2,
"C": 3,
"D": 4,
"E": 5,
"G": 6,
"H": 7,
"I": 8,
"K": 9,
"L": 10,
"M": 11,
"N": 12,
"O": 13,
"P": 14,
"Q": 15,
"R": 16,
"S": 17,
"T": 18,
"U": 19,
"V": 20,
"X": 21,
"Y": 22,
"[PAD]": 91,
"[UNK]": 90,
"|": 0,
"À": 23,
"Á": 24,
"Â": 25,
"Ã": 26,
"È": 27,
"É": 28,
"Ê": 29,
"Ì": 30,
"Í": 31,
"Ò": 32,
"Ó": 33,
"Ô": 34,
"Õ": 35,
"Ù": 36,
"Ú": 37,
"Ý": 38,
"Ă": 39,
"Đ": 40,
"Ĩ": 41,
"Ũ": 42,
"Ơ": 43,
"Ư": 44,
"Ạ": 45,
"Ả": 46,
"Ấ": 47,
"Ầ": 48,
"Ẩ": 49,
"Ẫ": 50,
"Ậ": 51,
"Ắ": 52,
"Ằ": 53,
"Ẳ": 54,
"Ẵ": 55,
"Ặ": 56,
"Ẹ": 57,
"Ẻ": 58,
"Ẽ": 59,
"Ế": 60,
"Ề": 61,
"Ể": 62,
"Ễ": 63,
"Ệ": 64,
"Ỉ": 65,
"Ị": 66,
"Ọ": 67,
"Ỏ": 68,
"Ố": 69,
"Ồ": 70,
"Ổ": 71,
"Ỗ": 72,
"Ộ": 73,
"Ớ": 74,
"Ờ": 75,
"Ở": 76,
"Ỡ": 77,
"Ợ": 78,
"Ụ": 79,
"Ủ": 80,
"Ứ": 81,
"Ừ": 82,
"Ử": 83,
"Ữ": 84,
"Ự": 85,
"Ỳ": 86,
"Ỵ": 87,
"Ỷ": 88,
"Ỹ": 89
}