add tokenizer

vocab.json

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