add tokenizer

vocab.json

@@ -1 +1 @@
-{"*": 0, "x": 1, "g": 2, "l": 3, "k": 4, "w": 5, "f": 6, "p": 7, "n": 8, "h": 9, "\n": 10, "d": 11, "'": 12, "e": 13, "q": 14, "i": 15, "c": 16, "b": 17, "j": 18, "u": 19, "r": 20, "y": 22, "m": 23, "s": 24, "a": 25, "v": 26, "t": 27, "o": 28, "|": 21, "[UNK]": 29, "[PAD]": 30}
+{"*": 0, "x": 1, "g": 2, "l": 3, "k": 4, "w": 5, "p": 6, "f": 7, "n": 8, "h": 9, "\n": 10, "d": 11, "'": 12, "e": 13, "q": 14, "i": 15, "c": 16, "b": 17, "j": 18, "u": 19, "r": 20, "m": 22, "y": 23, "s": 24, "a": 25, "v": 26, "t": 27, "o": 28, "|": 21, "[UNK]": 29, "[PAD]": 30}