remove result section and change meta-llama 3.1 to llama 3.1

tools/benchmarks/llm_eval_harness/meta_eval/eval_config.yaml

@@ -1,7 +1,7 @@
-model_name: "meta-llama/Meta-Llama-3.1-8B-Instruct" # The name of the model to evaluate. This must be a valid Meta Llama 3 based model name in the HuggingFace model hub."
+model_name: "meta-llama/Llama-3.1-8B-Instruct" # The name of the model to evaluate. This must be a valid Meta Llama 3 based model name in the HuggingFace model hub."
 
-evals_dataset: "meta-llama/Meta-Llama-3.1-8B-Instruct-evals" # The name of the 3.1 evals dataset to evaluate, please make sure this eval dataset corresponds to the model loaded. This must be a valid Meta Llama 3.1 evals dataset name in the Llama 3.1 Evals collection.
-# Must be one of the following ["meta-llama/Meta-Llama-3.1-8B-Instruct-evals","meta-llama/Meta-Llama-3.1-70B-Instruct-evals","meta-llama/Meta-Llama-3.1-405B-Instruct-evals","meta-llama/Meta-Llama-3.1-8B-evals","meta-llama/Meta-Llama-3.1-70B-evals","meta-llama/Meta-Llama-3.1-405B-evals"]
+evals_dataset: "meta-llama/Llama-3.1-8B-Instruct-evals" # The name of the 3.1 evals dataset to evaluate, please make sure this eval dataset corresponds to the model loaded. This must be a valid Meta Llama 3.1 evals dataset name in the Llama 3.1 Evals collection.
+# Must be one of the following ["meta-llama/Llama-3.1-8B-Instruct-evals","meta-llama/Llama-3.1-70B-Instruct-evals","meta-llama/Llama-3.1-405B-Instruct-evals","meta-llama/Llama-3.1-8B-evals","meta-llama/Llama-3.1-70B-evals","meta-llama/Llama-3.1-405B-evals"]
 
 tasks: "meta_instruct" # Available tasks for instruct model: "meta_math_hard", "meta_gpqa", "meta_mmlu_pro_instruct", "meta_ifeval"; or just use "meta_instruct" to run all of them.
 # Available tasks for pretrain model: "meta_bbh", "meta_mmlu_pro_pretrain"; or just use "meta_pretrain" to run all of them.

tools/benchmarks/llm_eval_harness/meta_eval/meta_template/bbh/bbh_3shot_cot.yaml

@@ -1,5 +1,5 @@
-dataset_path: meta-llama/Meta-Llama-3.1-8B-evals
-dataset_name: Meta-Llama-3.1-8B-evals__bbh__details
+dataset_path: meta-llama/Llama-3.1-8B-evals
+dataset_name: Llama-3.1-8B-evals__bbh__details
 task: meta_bbh
 output_type: generate_until
 process_docs: !function utils.process_docs

tools/benchmarks/llm_eval_harness/meta_eval/meta_template/gpqa_cot/gpqa_0shot_cot.yaml

@@ -1,5 +1,5 @@
-dataset_path: meta-llama/Meta-Llama-3.1-8B-Instruct-evals
-dataset_name: Meta-Llama-3.1-8B-Instruct-evals__gpqa__details
+dataset_path: meta-llama/Llama-3.1-8B-Instruct-evals
+dataset_name: Llama-3.1-8B-Instruct-evals__gpqa__details
 task: meta_gpqa
 output_type: generate_until
 process_docs: !function utils.process_docs

tools/benchmarks/llm_eval_harness/meta_eval/meta_template/mmlu_pro/mmlu_pro_5shot_cot_instruct.yaml

@@ -1,6 +1,6 @@
 task: meta_mmlu_pro_instruct
-dataset_path: meta-llama/Meta-Llama-3.1-8B-Instruct-evals
-dataset_name: Meta-Llama-3.1-8B-Instruct-evals__mmlu_pro__details
+dataset_path: meta-llama/Llama-3.1-8B-Instruct-evals
+dataset_name: Llama-3.1-8B-Instruct-evals__mmlu_pro__details
 test_split: latest
 output_type: generate_until
 process_docs: !function utils.process_docs

tools/benchmarks/llm_eval_harness/meta_eval/meta_template/mmlu_pro/mmlu_pro_5shot_cot_pretrain.yaml

@@ -1,6 +1,6 @@
 task: meta_mmlu_pro_pretrain
-dataset_path: meta-llama/Meta-Llama-3.1-8B-evals
-dataset_name: Meta-Llama-3.1-8B-evals__mmlu_pro__details
+dataset_path: meta-llama/Llama-3.1-8B-evals
+dataset_name: Llama-3.1-8B-evals__mmlu_pro__details
 test_split: latest
 output_type: generate_until
 process_docs: !function utils.process_docs

tools/benchmarks/llm_eval_harness/meta_eval/prepare_meta_eval.py

@@ -16,12 +16,12 @@ from datasets import Dataset, load_dataset
 def get_ifeval_data(model_name, output_dir):
     print(f"preparing the ifeval data using {model_name}'s evals dataset")
     if model_name not in [
-        "Meta-Llama-3.1-8B-Instruct",
-        "Meta-Llama-3.1-70B-Instruct",
-        "Meta-Llama-3.1-405B-Instruct",
+        "Llama-3.1-8B-Instruct",
+        "Llama-3.1-70B-Instruct",
+        "Llama-3.1-405B-Instruct",
     ]:
         raise ValueError(
-            "Only Meta-Llama-3.1-8B-Instruct, Meta-Llama-3.1-70B-Instruct, Meta-Llama-3.1-405B-Instruct models are supported for IFEval"
+            "Only Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Llama-3.1-405B-Instruct models are supported for IFEval"
         )
     original_dataset_name = "wis-k/instruction-following-eval"
     meta_dataset_name = f"meta-llama/{model_name}-evals"
@@ -59,12 +59,12 @@ def get_ifeval_data(model_name, output_dir):
 def get_math_data(model_name, output_dir):
     print(f"preparing the math data using {model_name}'s evals dataset")
     if model_name not in [
-        "Meta-Llama-3.1-8B-Instruct",
-        "Meta-Llama-3.1-70B-Instruct",
-        "Meta-Llama-3.1-405B-Instruct",
+        "Llama-3.1-8B-Instruct",
+        "Llama-3.1-70B-Instruct",
+        "Llama-3.1-405B-Instruct",
     ]:
         raise ValueError(
-            "Only Meta-Llama-3.1-8B-Instruct, Meta-Llama-3.1-70B-Instruct, Meta-Llama-3.1-405B-Instruct models are supported for MATH_hard"
+            "Only Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Llama-3.1-405B-Instruct models are supported for MATH_hard"
         )
     original_dataset_name = "lighteval/MATH-Hard"
     meta_dataset_name = f"meta-llama/{model_name}-evals"
@@ -130,7 +130,7 @@ def change_yaml(args, base_name):
         with open(output_path, "w") as output:
             for line in lines:
                 output.write(
-                    line.replace("Meta-Llama-3.1-8B", base_name).replace(
+                    line.replace("Llama-3.1-8B", base_name).replace(
                         "WORK_DIR", str(yaml_dir)
                     )
                 )
@@ -208,12 +208,12 @@ if __name__ == "__main__":
     if not os.path.exists(args.template_dir):
         raise ValueError("The template_dir does not exist, please check the path")
     if args.evals_dataset not in [
-        "meta-llama/Meta-Llama-3.1-8B-Instruct-evals",
-        "meta-llama/Meta-Llama-3.1-70B-Instruct-evals",
-        "meta-llama/Meta-Llama-3.1-405B-Instruct-evals",
-        "meta-llama/Meta-Llama-3.1-8B-evals",
-        "meta-llama/Meta-Llama-3.1-70B-evals",
-        "meta-llama/Meta-Llama-3.1-405B-evals",
+        "meta-llama/Llama-3.1-8B-Instruct-evals",
+        "meta-llama/Llama-3.1-70B-Instruct-evals",
+        "meta-llama/Llama-3.1-405B-Instruct-evals",
+        "meta-llama/Llama-3.1-8B-evals",
+        "meta-llama/Llama-3.1-70B-evals",
+        "meta-llama/Llama-3.1-405B-evals",
     ]:
         raise ValueError(
             "The evals dataset is not valid, please double check the name, must use the name in the Llama 3.1 Evals collection"