Update requirements.txt to specify setuptools version 65.0.0 or higher for compatibility with APScheduler. 1d6a538 djstrong commited on 11 days ago
Enhance model retrieval logic in read_evals.py to support dict-based model_args and improve org_and_model extraction; update .gitignore to exclude eval-results files. 5afbc08 djstrong commited on 11 days ago
Downgrade gradio and sdk_version in README.md and requirements.txt to version 4.4.0 for compatibility. d395db2 djstrong commited on Jan 29
Refactor update_table function parameters for improved readability and add api_name parameter to leaderboard table updates. 58fbedf djstrong commited on Jan 29
Add non-interactive backend for matplotlib in app.py and restrict numpy version in requirements.txt to below 2.0 40f33b6 djstrong commited on Jan 29
Update requirements.txt to upgrade gradio to version 4.36.0 and ensure gradio_client is compatible with version 0.7.0 or higher. d70f757 djstrong commited on Jan 29
Change ColumnContent dataclass to be immutable by adding frozen=True decorator 0cd768c djstrong commited on Jan 29
Upgrade transformers version in requirements.txt to 4.45.0 and remove specific git dependency. 414c08d djstrong commited on Jan 29
Upgrade pandas version in requirements.txt and add runtime.txt to specify Python version 3.12. 6c55606 djstrong commited on Jan 29
Update requirements.txt to include setuptools and upgrade numpy to version 1.26.0; enhance check_validity.py to recognize 'Qwen3-' model names. 4ce3209 djstrong commited on Jan 29
Refactor calc_avg.py to define new tasks and implement task retrieval logic 49c50f6 djstrong commited on Mar 25, 2025
Add calc_avg.py for average score calculation and refactor task retrieval in about.py b9262b0 djstrong commited on Mar 25, 2025