rwang97's picture
add tokenizer
b7249fa
raw history blame
No virus
268 Bytes
{"t": 0, "m": 1, "z": 2, "w": 3, "y": 4, "n": 5, "r": 6, "s": 7, "l": 8, "u": 9, "k": 10, "v": 11, "q": 12, "e": 13, "x": 14, "g": 15, "'": 16, "o": 18, "f": 19, "a": 20, "b": 21, "p": 22, "d": 23, "c": 24, "i": 25, "j": 26, "h": 27, "|": 17, "[UNK]": 28, "[PAD]": 29}