add tokenizer

vocab.json

@@ -1 +1 @@
-{"n": 0, "g": 2, "v": 3, "x": 4, "p": 5, "e": 6, "c": 7, "f": 8, "j": 9, "！": 10, "k": 11, "r": 12, "b": 13, "t": 14, "o": 15, "m": 16, "s": 17, "u": 18, "h": 19, "l": 20, "d": 21, "i": 22, "z": 23, "a": 24, "y": 25, "w": 26, "|": 1, "[UNK]": 27, "[PAD]": 28}
+{"x": 0, "d": 1, "t": 2, "p": 3, "r": 4, "w": 5, "e": 6, "j": 7, "k": 8, "f": 9, "y": 10, "z": 11, "b": 12, "c": 13, "g": 14, "！": 15, "n": 16, "l": 17, "i": 18, "u": 19, "o": 20, "v": 21, "a": 22, "h": 23, "m": 24, "s": 26, "|": 25, "[UNK]": 27, "[PAD]": 28}