add tokenizer

vocab.json

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