add tokenizer

vocab.json

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