finetuned_model / vocab.json
hungadc's picture
Upload tokenizer
f9d43fe verified
{
"'": 32,
"[PAD]": 96,
"[UNK]": 95,
"a": 18,
"b": 94,
"c": 62,
"d": 42,
"e": 19,
"f": 0,
"g": 67,
"h": 6,
"i": 39,
"j": 46,
"k": 28,
"l": 5,
"m": 37,
"n": 72,
"o": 59,
"p": 16,
"q": 55,
"r": 1,
"s": 66,
"t": 45,
"u": 15,
"v": 52,
"w": 64,
"x": 48,
"y": 40,
"z": 54,
"|": 17,
"à": 41,
"á": 85,
"â": 4,
"ã": 79,
"è": 90,
"é": 47,
"ê": 86,
"ì": 63,
"í": 83,
"ò": 87,
"ó": 25,
"ô": 88,
"õ": 21,
"ù": 92,
"ú": 13,
"ý": 36,
"ă": 38,
"đ": 78,
"ĩ": 80,
"ũ": 51,
"ơ": 10,
"ư": 56,
"ạ": 91,
"ả": 9,
"ấ": 57,
"ầ": 53,
"ẩ": 93,
"ẫ": 77,
"ậ": 31,
"ắ": 60,
"ằ": 8,
"ẳ": 35,
"ẵ": 14,
"ặ": 33,
"ẹ": 82,
"ẻ": 68,
"ẽ": 75,
"ế": 50,
"ề": 69,
"ể": 71,
"ễ": 89,
"ệ": 73,
"ỉ": 61,
"ị": 7,
"ọ": 74,
"ỏ": 27,
"ố": 3,
"ồ": 22,
"ổ": 11,
"ỗ": 58,
"ộ": 65,
"ớ": 81,
"ờ": 84,
"ở": 34,
"ỡ": 29,
"ợ": 23,
"ụ": 43,
"ủ": 12,
"ứ": 44,
"ừ": 76,
"ử": 20,
"ữ": 49,
"ự": 24,
"ỳ": 70,
"ỵ": 2,
"ỷ": 26,
"ỹ": 30
}