minor fixes to satisify pre-commit

main.py

@@ -10,6 +10,7 @@ from lm_eval.logger import eval_logger
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 ALL_TASKS = sorted(list(TASK_REGISTRY.keys()) + list(GROUP_REGISTRY.keys()))
 
+
 class MultiChoice:
     def __init__(self, choices):
         self.choices = choices
@@ -21,7 +22,7 @@ class MultiChoice:
                 eval_logger.warning("{} is not in task list.".format(value))
                 eval_logger.info(f"Available tasks to choose:")
                 # for choice in self.choices:
-                    # eval_logger.info(f"    {choice}")
+                # eval_logger.info(f"    {choice}")
                 eval_logger.info(ALL_TASKS)
         return True
 

scripts/write_out.py

@@ -32,10 +32,10 @@ def main():
         task_names = args.tasks.split(",")
     task_dict = tasks.get_task_dict(task_names)
 
-    description_dict = {}
-    if args.description_dict_path:
-        with open(args.description_dict_path, "r") as f:
-            description_dict = json.load(f)
+    # description_dict = {}
+    # if args.description_dict_path:
+    #     with open(args.description_dict_path, "r") as f:
+    #         description_dict = json.load(f)
 
     os.makedirs(args.output_base_path, exist_ok=True)
     for task_name, task in task_dict.items():
@@ -55,11 +55,11 @@ def main():
 
         docs = join_iters(iters)
 
-        description = (
-            description_dict[task_name]
-            if description_dict and task_name in description_dict
-            else ""
-        )
+        # description = (
+        #     description_dict[task_name]
+        #     if description_dict and task_name in description_dict
+        #     else ""
+        # )
 
         with open(os.path.join(args.output_base_path, task_name), "w") as f:
             for i, doc in (

templates/new_yaml_task/README.md

@@ -28,7 +28,7 @@ For adding novel benchmarks/datasets to the library:
 * [ ] Is the task an existing benchmark in the literature?
   * [ ] Have you referenced the original paper that introduced the task?
   * [ ] If yes, does the original paper provide a reference implementation? If so, have you checked against the reference implementation and documented how to run such a test?
-  
+
 
 If other tasks on this dataset are already supported:
 * [ ] Is the "Main" variant of this task clearly denoted?