Arnold's picture
add tokenizer
f7924ab
{"t": 0, "o": 1, "ƴ": 2, "y": 3, "’": 4, "v": 5, "j": 6, "w": 7, "—": 8, "f": 9, "n": 10, "m": 11, "ƙ": 13, "h": 14, "l": 15, "ɗ": 16, "z": 17, "q": 18, "d": 19, "e": 20, "c": 21, "x": 22, "í": 23, "r": 24, "g": 25, "u": 26, "a": 27, "s": 28, "b": 29, "i": 30, "'": 31, "k": 32, "ɓ": 33, "ʻ": 34, "p": 35, "|": 12, "[UNK]": 36, "[PAD]": 37}