add tokenizer

vocab.json

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