add tokenizer

vocab.json

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