awacke1's picture
add tokenizer
da8cb65
{"l": 0, "i": 1, "u": 2, "o": 3, "n": 4, "p": 5, "m": 6, "k": 7, "c": 8, "e": 9, "r": 10, "v": 11, "g": 12, "q": 13, "d": 14, "t": 15, "w": 16, "a": 17, "'": 18, "f": 19, "j": 20, "h": 21, "z": 22, "b": 23, "s": 24, "y": 25, "x": 27, "|": 26, "[UNK]": 28, "[PAD]": 29}