add tokenizer

vocab.json

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