Support glm4.1v and glm4.5v (#8798)

Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Chang Su <csu272@usc.edu>

benchmark/mmmu/eval_utils.py

@@ -35,6 +35,7 @@ class EvalArgs:
     profile: bool = False
     profile_number: int = 5
     concurrency: int = 1
+    response_answer_regex: str = "(.*)"
     lora_path: Optional[str] = None
 
     @staticmethod
@@ -92,6 +93,12 @@ class EvalArgs:
             default=EvalArgs.concurrency,
             help="Number of concurrent requests to make during evaluation. Default is 1, which means no concurrency.",
         )
+        parser.add_argument(
+            "--response-answer-regex",
+            type=str,
+            default=EvalArgs.response_answer_regex,
+            help="Specific regex to capture the answer from the response, string",
+        )
         parser.add_argument(
             "--lora-path",
             type=str,