add tokenizer

vocab.json

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