Upload tokenizer
9f735e3
verified
|
{ |
|
"'": 9, |
|
"4": 6, |
|
"[PAD]": 97, |
|
"[UNK]": 96, |
|
"a": 36, |
|
"b": 93, |
|
"c": 79, |
|
"d": 55, |
|
"e": 14, |
|
"f": 42, |
|
"g": 49, |
|
"h": 25, |
|
"i": 85, |
|
"j": 27, |
|
"k": 48, |
|
"l": 20, |
|
"m": 90, |
|
"n": 69, |
|
"o": 92, |
|
"p": 61, |
|
"q": 4, |
|
"r": 60, |
|
"s": 89, |
|
"t": 52, |
|
"u": 80, |
|
"v": 81, |
|
"w": 57, |
|
"x": 24, |
|
"y": 94, |
|
"z": 76, |
|
"|": 75, |
|
"à": 26, |
|
"á": 47, |
|
"â": 54, |
|
"ã": 67, |
|
"è": 78, |
|
"é": 34, |
|
"ê": 71, |
|
"ì": 56, |
|
"í": 19, |
|
"ò": 77, |
|
"ó": 51, |
|
"ô": 70, |
|
"õ": 8, |
|
"ù": 68, |
|
"ú": 44, |
|
"ý": 29, |
|
"ă": 64, |
|
"đ": 43, |
|
"ĩ": 65, |
|
"ũ": 53, |
|
"ơ": 13, |
|
"ư": 11, |
|
"ạ": 0, |
|
"ả": 74, |
|
"ấ": 84, |
|
"ầ": 37, |
|
"ẩ": 3, |
|
"ẫ": 86, |
|
"ậ": 35, |
|
"ắ": 10, |
|
"ằ": 63, |
|
"ẳ": 58, |
|
"ẵ": 23, |
|
"ặ": 91, |
|
"ẹ": 12, |
|
"ẻ": 33, |
|
"ẽ": 31, |
|
"ế": 72, |
|
"ề": 83, |
|
"ể": 39, |
|
"ễ": 45, |
|
"ệ": 73, |
|
"ỉ": 15, |
|
"ị": 50, |
|
"ọ": 87, |
|
"ỏ": 28, |
|
"ố": 2, |
|
"ồ": 22, |
|
"ổ": 18, |
|
"ỗ": 40, |
|
"ộ": 38, |
|
"ớ": 7, |
|
"ờ": 16, |
|
"ở": 88, |
|
"ỡ": 32, |
|
"ợ": 59, |
|
"ụ": 62, |
|
"ủ": 5, |
|
"ứ": 82, |
|
"ừ": 46, |
|
"ử": 17, |
|
"ữ": 95, |
|
"ự": 30, |
|
"ỳ": 41, |
|
"ỵ": 66, |
|
"ỷ": 1, |
|
"ỹ": 21 |
|
} |
|
|