add tokenizer

vocab.json

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