GitHub - ash80/RLHF_in_notebooks: RLHF (Supervised fine-tuning, reward model, and PPO) step-by-st...
https://github.com/ash80/RLHF_in_notebooks RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks - ash80/RLHF_in_notebooks