add tokenizer

vocab.json

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