updated to gradio; python 3.11; visual improvements

added phi4

revised dataset

update model_operations.py for new llms

update summary generation for new models

Merge branch 'main' of hf.co:spaces/vectara/leaderboard

minor fix to work for recent models

removed filters and columns we dont need

Update src/display/about.py

minor update for new models; postprocessing for md format

minor fix

minor update for src/model_operations.py

update for HF HHEM2.1

update text description

update backend

upload csv to leaderboard_results

merge with 'main'

minor updates

minor fix

minor fix

minor updates in publishing and logging results

minor update and extend to support different APIs

Update src/display/about.py

Update src/display/about.py

Update src/display/about.py

Update src/display/about.py

Update src/display/about.py

Update src/display/about.py

Updated bibtex

Updated bibtex

Added bibtex

Updated bibtex citation

Update src/display/about.py

Update src/display/about.py

modified about.py

Modified about.py so that it displays (%) in columns.

Fixed the leaderboard filtering functionality. Modified filter_models() function in app.py/

modified the evaluation pipelines.

Added citations

Updated about.py

Edited README and added reproducibility functionality in main_backend.py

modified read_evals.py

Refine the code style

Implemented litellm pipeline

Edited README and removed error-rate metric

modified is_model_on_hub()

changed back to TOKEN

changed to HF_TOKEN

modified check_validity.py and added sample dataset to test functionality

Integrated backend pipelines - error occurs during model submission. (Debugging needed).