Update README.md
#6
by
Haoxiang-Wang - opened
README.md
CHANGED
|
@@ -2,6 +2,10 @@
|
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
This reward function can be used for RLHF, including PPO, iterative SFT, iterative DPO.
|
| 6 |
|
| 7 |
The license is derived from `PKU-Alignment/PKU-SafeRLHF-30K`.
|
|
|
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
* **Paper**: [RLHF Workflow: From Reward Modeling to Online RLHF](https://arxiv.org/pdf/2405.07863) (Published in TMLR, 2024)
|
| 6 |
+
* **Authors**: Hanze Dong*, Wei Xiong*, Bo Pang*, Haoxiang Wang*, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang
|
| 7 |
+
* **Code**: https://github.com/RLHFlow/RLHF-Reward-Modeling/
|
| 8 |
+
|
| 9 |
This reward function can be used for RLHF, including PPO, iterative SFT, iterative DPO.
|
| 10 |
|
| 11 |
The license is derived from `PKU-Alignment/PKU-SafeRLHF-30K`.
|