radhakri119's picture
add tokenizer
381cc8f
raw history blame
No virus
268 Bytes
{"k": 0, "q": 2, "r": 3, "h": 4, "a": 5, "s": 6, "l": 7, "j": 8, "o": 9, "z": 10, "d": 11, "f": 12, "m": 13, "b": 14, "p": 15, "'": 16, "w": 17, "t": 18, "e": 19, "u": 20, "i": 21, "n": 22, "y": 23, "g": 24, "v": 25, "c": 26, "x": 27, "|": 1, "[UNK]": 28, "[PAD]": 29}