add tokenizer

vocab.json

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