update

app.py

@@ -476,6 +476,6 @@ with demo:
 
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
-#scheduler.add_job(update_dynamic_files, "cron", minute=30) # launched every hour on the hour
+scheduler.add_job(update_dynamic_files, "cron", minute=30) # launched every hour on the hour
 scheduler.start()
 demo.queue(default_concurrency_limit=40).launch()

src/about.py

@@ -77,8 +77,8 @@ For all these evaluations, a higher score is a better score. We chose these benc
 
 ## Details and logs
 You can find:
-- detailed numerical results in the results Hugging Face dataset: https://huggingface.co/datasets/open-cn-llm-leaderboard/results
-- community queries and running status in the requests Hugging Face dataset: https://huggingface.co/datasets/open-cn-llm-leaderboard/requests
+- detailed numerical results in the results Hugging Face dataset: https://huggingface.co/datasets/open-cn-llm-leaderboard/vlm_results
+- community queries and running status in the requests Hugging Face dataset: https://huggingface.co/datasets/open-cn-llm-leaderboard/vlm_requests
 
 ## Reproducibility