add tokenizer

vocab.json

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