add tokenizer

vocab.json

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