add tokenizer

vocab.json

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