add tokenizer

vocab.json

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