machinelearningzuu's picture
add tokenizer
15f3750
raw
history blame contribute delete
277 Bytes
{"f": 0, "k": 1, "j": 2, "d": 3, ".": 4, "b": 5, "c": 6, "r": 7, "p": 8, "h": 10, "i": 11, "v": 12, "n": 13, "a": 14, "q": 15, "e": 16, "t": 17, "w": 18, "o": 19, "x": 20, "z": 21, "s": 22, "u": 23, "m": 24, "l": 25, "y": 26, "g": 27, "'": 28, "|": 9, "[UNK]": 29, "[PAD]": 30}