add tokenizer

vocab.json

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