Add new dataset MMLU-SR tasks (#2032)

* add mmlusr tasks

* renamed all tasks names in mmlusr

* edit format and readme

* added mmlu_sr

* mmlu_sr -> mmlusr

* update

---------
Co-authored-by: lintangsutawika <lintang@eleuther.ai>

lm_eval/tasks/mmlusr/question_only/question_only_virology.yaml

+"dataset_name": "question_only_virology"
+"description": "The following are multiple choice questions (with answers) about virology.\n\
+  \n"
+"tag": "mmlusr_question_only_other_tasks"
+"include": "_mmlusr_q_yml"
+"task": "mmlusr_question_only_virology"
+"task_alias": "virology"

lm_eval/tasks/mmlusr/question_only/question_only_world_religions.yaml

+"dataset_name": "question_only_world_religions"
+"description": "The following are multiple choice questions (with answers) about world\
+  \ religions.\n\n"
+"tag": "mmlusr_question_only_humanities_tasks"
+"include": "_mmlusr_q_yml"
+"task": "mmlusr_question_only_world_religions"
+"task_alias": "world religions"

lm_eval/tasks/mmlusr/question_only/utils.py

+import datasets
+
+
+def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:
+    def _helper(doc):
+        # Assuming that the 'answer' field in the dataset now contains numbers 0-3 instead of 'A', 'B', 'C', 'D'
+        answer_list = ["A", "B", "C", "D"]
+        # Convert numeric index to corresponding letter
+        answer_index = int(doc["answer"])  # Make sure the answer is an integer
+        answer_letter = answer_list[answer_index]
+
+        out_doc = {
+            "questions": doc["question"],
+            "choices": [doc["choice1"], doc["choice2"], doc["choice3"], doc["choice4"]],
+            "answer": answer_letter,  # Include the letter for clarity
+        }
+        return out_doc
+
+    return dataset.map(_helper)