add tokenizer

vocab.json

@@ -1 +1 @@
-{"e": 0, "o": 1, "n": 2, "i": 3, "y": 4, "d": 5, "m": 7, "k": 8, "h": 9, "v": 10, "a": 11, "l": 12, "r": 13, "q": 14, "p": 15, "b": 16, "c": 17, "x": 18, "f": 19, "t": 20, "w": 21, "s": 22, "g": 24, "j": 25, "u": 26, "z": 27, "[UNK]": 28, "[PAD]": 29, "|": 6}
+{"u": 0, "h": 1, "q": 3, "z": 5, "k": 6, "y": 7, "e": 8, "j": 9, "a": 10, "f": 11, "d": 12, "s": 13, "c": 14, "m": 15, "v": 16, "o": 17, "l": 18, "i": 19, "x": 20, "r": 21, "b": 22, "w": 23, "g": 24, "t": 25, "p": 26, "n": 27, "[UNK]": 28, "[PAD]": 29, "|": 2}