add tokenizer

vocab.json

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