add tokenizer

vocab.json

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