add tokenizer

vocab.json

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