add tokenizer

vocab.json

@@ -1 +1 @@
-{"r": 0, "5": 1, "3": 2, "p": 3, "g": 4, "e": 5, "b": 6, "0": 8, "j": 9, "w": 10, "d": 11, "q": 12, "c": 13, "x": 14, "6": 15, "s": 16, "1": 17, "a": 18, "m": 19, "4": 20, "n": 21, "i": 22, "9": 23, "f": 24, "2": 25, "k": 26, "l": 27, "8": 28, "'": 29, "y": 30, "z": 31, "h": 32, "u": 33, "o": 34, "v": 35, "t": 36, "|": 7, "[UNK]": 37, "[PAD]": 38}
+{"p": 0, "d": 2, "h": 3, "1": 4, "g": 5, "v": 6, "i": 7, "8": 8, "s": 9, "a": 10, "e": 11, "x": 12, "t": 13, "2": 14, "0": 15, "9": 16, "m": 17, "6": 18, "k": 19, "z": 20, "3": 21, "u": 22, "4": 23, "l": 24, "n": 25, "q": 26, "j": 27, "y": 28, "r": 29, "f": 30, "b": 31, "w": 32, "'": 33, "o": 34, "c": 35, "5": 36, "|": 1, "[UNK]": 37, "[PAD]": 38}