metadata
license: mit
language:
- en
tags:
- ODIN
- RLHF
- PPO
- Developed by: Lichang-Chen and Chen Zhu
- Model type: RLHF model.
- Language(s) (NLP): English
- Finetuned from model: Vicuna-7b
Model Sources [optional]
- Repository: ODIN
- Paper: ODIN: Disentangled Reward Mitigates Hacking in RLHF