add tokenizer

vocab.json

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