CapitainData's picture
add tokenizer
9c93dd0
raw
history blame
261 Bytes
{"n": 0, "c": 1, "s": 2, "k": 3, "g": 4, "t": 5, "z": 6, "l": 7, "i": 8, "'": 9, "h": 10, "f": 11, "w": 12, "m": 13, "y": 14, "r": 15, "b": 16, "u": 17, "o": 19, "a": 20, "v": 21, "p": 22, "’": 23, "e": 24, "j": 25, "d": 26, "|": 18, "[UNK]": 27, "[PAD]": 28}