thivy's picture
add tokenizer
fc0f647
raw
history blame contribute delete
No virus
362 Bytes
{"c": 0, "ò": 1, "b": 2, "ê": 3, "i": 4, "f": 5, "k": 6, "v": 7, "o": 8, "l": 9, "é": 10, "a": 11, "d": 12, "æ": 13, "ó": 14, "t": 15, "p": 16, "q": 17, "n": 18, "§": 19, "u": 20, "x": 21, "s": 22, "y": 23, "…": 24, "h": 25, "g": 26, "m": 27, "ø": 28, "å": 29, "ô": 30, "e": 31, "á": 33, "r": 34, "ä": 35, "j": 36, "|": 32, "[UNK]": 37, "[PAD]": 38}