czlwang's picture
add tokenizer
a8a1155
raw
history blame contribute delete
268 Bytes
{"r": 0, "z": 1, "t": 3, "d": 4, "s": 5, "b": 6, "j": 7, "x": 8, "c": 9, "a": 10, "n": 11, "u": 12, "v": 13, "y": 14, "q": 15, "'": 16, "e": 17, "f": 18, "i": 19, "h": 20, "k": 21, "l": 22, "g": 23, "o": 24, "m": 25, "w": 26, "p": 27, "|": 2, "[UNK]": 28, "[PAD]": 29}