add tokenizer

vocab.json

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