add tokenizer

vocab.json

@@ -1 +1 @@
-{"z": 0, "4": 1, "7": 2, "8": 3, "6": 4, "w": 5, "i": 6, "£": 7, "q": 8, "9": 9, "h": 10, "j": 11, "3": 12, "g": 13, "y": 14, "p": 15, "b": 16, "s": 17, "n": 18, "v": 19, "o": 20, "0": 21, "c": 22, "1": 23, "r": 24, "m": 26, "f": 27, "2": 28, "5": 29, "a": 30, "e": 31, "l": 32, "t": 33, "k": 34, "u": 35, "x": 36, "d": 37, "|": 25, "[UNK]": 38, "[PAD]": 39}
+{"h": 0, "£": 1, "a": 2, "p": 3, "f": 4, "v": 5, "6": 6, "z": 7, "y": 8, "n": 9, "t": 10, "c": 11, "i": 12, "b": 13, "0": 14, "8": 15, "m": 16, "g": 17, "x": 18, "q": 19, "9": 20, "3": 21, "4": 22, "u": 23, "1": 24, "2": 26, "d": 27, "s": 28, "k": 29, "w": 30, "7": 31, "r": 32, "l": 33, "5": 34, "j": 35, "o": 36, "e": 37, "|": 25, "[UNK]": 38, "[PAD]": 39}