tomyc's picture
add tokenizer
24dba29
{"q": 0, "f": 1, "e": 2, "j": 3, "a": 4, "h": 5, "x": 6, "z": 7, "l": 8, "g": 10, "k": 11, "m": 12, "w": 13, "s": 14, "i": 15, "'": 16, "o": 17, "c": 18, "d": 19, "p": 20, "y": 21, "b": 22, "v": 23, "u": 24, "n": 25, "t": 26, "r": 27, "|": 9, "[UNK]": 28, "[PAD]": 29}