add tokenizer

vocab.json

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