add tokenizer

vocab.json

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