add tokenizer

vocab.json

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