add tokenizer

vocab.json

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