File size: 365 Bytes
7b5d647
 
64515d1
 
 
7b5d647
 
64515d1
1
2
3
4
5
6
7
8
---
library_name: transformers
license: mit
datasets:
- hendrydong/preference_700K
---

This is the bandit reward 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.