yyqoni/rlhflow-llama-3-sft-8b-v2-bandit-ppo-60k

This is the bandit reward based ppo model introduced in the preprint Segmenting Text and Learning Their Rewards for Improved RLHF in Language Models (https://arxiv.org/abs/2501.02790). For more details, please visit our repository at https://github.com/yinyueqin/DenseRewardRLHF-PPO.