add tokenizer

vocab.json

@@ -1 +1 @@
-{"f": 0, "q": 1, "m": 2, "d": 3, "u": 4, "x": 5, "a": 6, "o": 7, "z": 8, "t": 9, "i": 10, "r": 11, "v": 12, "n": 13, "s": 14, "k": 15, "b": 16, "p": 17, "'": 18, "h": 19, "e": 20, "l": 21, "c": 22, "w": 24, "g": 25, "y": 26, "j": 27, "|": 23, "[UNK]": 28, "[PAD]": 29}
+{"z": 0, "s": 1, "u": 2, "i": 3, "q": 4, "d": 5, "p": 6, "k": 7, "n": 8, "j": 9, "o": 10, "w": 11, "y": 12, "f": 13, "g": 14, "a": 16, "v": 17, "m": 18, "e": 19, "r": 20, "'": 21, "c": 22, "h": 23, "t": 24, "x": 25, "l": 26, "b": 27, "|": 15, "[UNK]": 28, "[PAD]": 29}