add tokenizer

vocab.json

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