add tokenizer

vocab.json

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