add tokenizer

vocab.json

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