add tokenizer

vocab.json

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