emlinking's picture
Upload tokenizer
ae0630f verified
raw
history blame
717 Bytes
{
"-": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"8": 9,
"9": 10,
"[PAD]": 61,
"[UNK]": 60,
"a": 11,
"b": 12,
"e": 13,
"g": 14,
"h": 15,
"i": 16,
"j": 17,
"k": 18,
"l": 19,
"m": 20,
"n": 21,
"o": 22,
"p": 23,
"s": 24,
"t": 25,
"u": 26,
"|": 0,
"à": 27,
"á": 28,
"â": 29,
"è": 30,
"é": 31,
"ê": 32,
"ì": 33,
"í": 34,
"î": 35,
"ò": 36,
"ó": 37,
"ô": 38,
"ù": 39,
"ú": 40,
"û": 41,
"ā": 42,
"ē": 43,
"ī": 44,
"ı": 45,
"ń": 46,
"ň": 47,
"ō": 48,
"ő": 49,
"ū": 50,
"ǎ": 51,
"ǹ": 52,
"̀": 53,
"̂": 54,
"̄": 55,
"̋": 56,
"̍": 57,
"͘": 58,
"ḿ": 59
}