add tokenizer

vocab.json

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