add tokenizer

vocab.json

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