add tokenizer

vocab.json

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