add tokenizer

vocab.json

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