fix datasets

backend/app/config/hf_config.py

@@ -20,7 +20,7 @@ API = HfApi(token=HF_TOKEN)
 
 # Repository configuration
 QUEUE_REPO = f"{HF_ORGANIZATION}/llm-security-leaderboard-requests"
-AGGREGATED_REPO = f"{HF_ORGANIZATION}/llm-security-leaderboard-results"
+AGGREGATED_REPO = f"{HF_ORGANIZATION}/llm-security-leaderboard-contents"
 VOTES_REPO = f"{HF_ORGANIZATION}/llm-security-leaderboard-votes"
 OFFICIAL_PROVIDERS_REPO = f"{HF_ORGANIZATION}/llm-security-leaderboard-official-providers"
 

backend/app/services/leaderboard.py

@@ -17,10 +17,10 @@ class LeaderboardService:
         """Fetch raw leaderboard data from HuggingFace dataset"""
         try:
             logger.info(LogFormatter.section("FETCHING LEADERBOARD DATA"))
-            logger.info(LogFormatter.info(f"Loading dataset from {HF_ORGANIZATION}/contents"))
+            logger.info(LogFormatter.info(f"Loading dataset from {HF_ORGANIZATION}/llm-security-leaderboard-contents"))
             
             dataset = datasets.load_dataset(
-                f"{HF_ORGANIZATION}/contents",
+                f"{HF_ORGANIZATION}/llm-security-leaderboard-contents",
                 cache_dir=cache_config.get_cache_path("datasets")
             )["train"]
             
@@ -205,4 +205,4 @@ class LeaderboardService:
             
         except Exception as e:
             logger.error(LogFormatter.error(f"Failed to transform data for {data.get('fullname', 'Unknown')}", e))
-            raise
+            raise

backend/utils/analyze_prod_datasets.py

@@ -120,7 +120,7 @@ def main():
         # List of datasets to analyze
         datasets = [
             {
-                "id": f"{HF_ORGANIZATION}/contents",
+                "id": f"{HF_ORGANIZATION}/llm-security-leaderboard-contents",
                 "description": "Aggregated results"
             },
             {
@@ -167,4 +167,4 @@ def main():
         return []
 
 if __name__ == "__main__":
-    main() 
+    main() 

backend/utils/analyze_prod_models.py

@@ -31,13 +31,13 @@ def count_evaluated_models():
     """Count the number of evaluated models"""
     try:
         # Get dataset info
-        dataset_info = api.dataset_info(repo_id=f"{HF_ORGANIZATION}/contents", repo_type="dataset")
+        dataset_info = api.dataset_info(repo_id=f"{HF_ORGANIZATION}/llm-security-leaderboard-contents", repo_type="dataset")
         
         # Get file list
-        files = api.list_repo_files(f"{HF_ORGANIZATION}/contents", repo_type="dataset")
+        files = api.list_repo_files(f"{HF_ORGANIZATION}/llm-security-leaderboard-contents", repo_type="dataset")
         
         # Get last commit info
-        commits = api.list_repo_commits(f"{HF_ORGANIZATION}/contents", repo_type="dataset")
+        commits = api.list_repo_commits(f"{HF_ORGANIZATION}/llm-security-leaderboard-contents", repo_type="dataset")
         last_commit = next(commits, None)
         
         # Count lines in jsonl files
@@ -47,7 +47,7 @@ def count_evaluated_models():
                 try:
                     # Download file content
                     content = api.hf_hub_download(
-                        repo_id=f"{HF_ORGANIZATION}/contents",
+                        repo_id=f"{HF_ORGANIZATION}/llm-security-leaderboard-contents",
                         filename=file,
                         repo_type="dataset"
                     )
@@ -103,4 +103,4 @@ def main():
         return {"error": str(e)}
 
 if __name__ == "__main__":
-    main() 
+    main() 

backend/utils/sync_datasets_locally.py

@@ -29,6 +29,7 @@ DATASET_NAMES = [
     "llm-security-leaderboard-votes",
     "llm-security-leaderboard-requests",
     "llm-security-leaderboard-results",
+    "llm-security-leaderboard-contents",
     "llm-security-leaderboard-official-providers",
 ]