add tokenizer

vocab.json

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