Instructions to use siddharthmb/2026.RA.Fairness-GRPO-v2-Adapters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use siddharthmb/2026.RA.Fairness-GRPO-v2-Adapters with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Ctrl+K
v2 fairness-GRPO LoRA adapters: full lambda-frontier (lam1/lam05/lam0 ladders) + card
dbba5e5 verified