add tokenizer

vocab.json

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