add tokenizer

vocab.json

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