metadata
library_name: transformers
license: mit
datasets:
- argilla/ultrafeedback-binarized-preferences-cleaned
base_model:
- RLHFlow/LLaMA3-SFT-v2
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.