fr-gouv-coordination-ia/llm_leaderboard_fr
Update README.md
Update disclaimer
Add DEV prefix to space title
Merge pull request #20 from leaderboard-modeles-IA-francais/feature/better_regexp
Change GPQA metric
Merge pull request #19 from leaderboard-modeles-IA-francais/fix/filter
Update leaderboard.py
Merge pull request #18 from leaderboard-modeles-IA-francais/remove-precision
fix: remove unecessary info from submission form
feat: internationalisation of submission form
feat: internationlization for disclaimer
feat: add internationalisation for tooltips and UI components
feat: add internationalisation
fix: correct parsing of the model type
feat: add search bar
Merge pull request #13 from leaderboard-modeles-IA-francais/feature/postpro
filter name = clearML-musa
Filter was commented? mybad
Merge pull request #12 from leaderboard-modeles-IA-francais/feature/postpro
Oops IFEval FR
Until the requests status is not updated, we do not consider it
Remove tmp fix for path in results-dev
Compute metrics/normalization for the 3 tasks
Dummy flag to check if we display the evaluation
Do not seek normalize metric in the result.json
Print in leaderboard only results in folder Inria_Results
Readme updates and docker compose up
Force push when deploying
Push HEAD to remote main in prod deployment
Add bot as committer to fix dev deployment
Merge pull request #8 from leaderboard-modeles-IA-francais/repos-env-config
Make repositories names configurable by env
Merge pull request #7 from leaderboard-modeles-IA-francais/dev-prefix-deploy
Add "DEV" prefix in title when deploying to dev environment
Revert "Add DEV prefix to space title"
Merge pull request #6 from leaderboard-modeles-IA-francais/fix-import
Fix broken import
Merge pull request #5 from leaderboard-modeles-IA-francais/add-prod-monitoring
Add workflow for production deployment
Merge pull request #4 from leaderboard-modeles-IA-francais/add-prod-monitoring
Add back monitoring if DSN is defined
Merge pull request #3 from leaderboard-modeles-IA-francais/fix-missing-deps
Add missing dependencies to test tokenizer in model validation
Install PyTorch as a dependency
Fix deployment env variables
Add proper permissions to CI job
Add deployment to HF dev space
Add CI
Change metric name
Remove monitoring from dev
