add tokenizer

vocab.json

@@ -1 +1 @@
-{"d": 0, "2": 2, "4": 3, "g": 4, "e": 5, "l": 6, "s": 7, "j": 8, "6": 9, "3": 10, "r": 11, "v": 12, "o": 13, "w": 14, "c": 15, "n": 16, "y": 17, "b": 18, "k": 19, "f": 20, "t": 21, "x": 22, "m": 23, "z": 24, "u": 25, "'": 26, "a": 27, "5": 28, "i": 29, "p": 30, "q": 31, "h": 32, "|": 1, "[UNK]": 33, "[PAD]": 34}
+{"q": 0, "i": 1, "a": 2, "2": 3, "y": 4, "f": 5, "x": 6, "c": 7, "h": 8, "l": 9, "r": 10, "j": 11, "p": 12, "s": 13, "4": 14, "e": 15, "z": 16, "m": 18, "3": 19, "d": 20, "n": 21, "u": 22, "v": 23, "6": 24, "t": 25, "o": 26, "w": 27, "b": 28, "k": 29, "g": 30, "5": 31, "'": 32, "|": 17, "[UNK]": 33, "[PAD]": 34}