add tokenizer

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

vocab.json

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