add tokenizer

vocab.json

@@ -1 +1 @@
-{"u": 0, "h": 1, "q": 3, "z": 5, "k": 6, "y": 7, "e": 8, "j": 9, "a": 10, "f": 11, "d": 12, "s": 13, "c": 14, "m": 15, "v": 16, "o": 17, "l": 18, "i": 19, "x": 20, "r": 21, "b": 22, "w": 23, "g": 24, "t": 25, "p": 26, "n": 27, "[UNK]": 28, "[PAD]": 29, "|": 2}
+{"b": 0, "i": 1, "u": 2, "s": 3, "k": 4, "c": 5, "r": 6, "m": 7, "p": 9, "y": 10, "w": 11, "z": 12, "t": 13, "f": 14, "n": 15, "g": 16, "v": 17, "h": 18, "d": 19, "e": 20, "o": 21, "x": 22, "l": 23, "j": 24, "q": 25, "a": 26, "[UNK]": 28, "[PAD]": 29, "|": 8}