add tokenizer

vocab.json

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