Commit
•
f5da9fb
1
Parent(s):
964f159
Update README.md
Browse files
README.md
CHANGED
@@ -2,4 +2,19 @@
|
|
2 |
license: cc-by-nc-nd-3.0
|
3 |
---
|
4 |
# SFR-SFT-LLaMA-3-8B-R
|
5 |
-
This is the SFT model for Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: cc-by-nc-nd-3.0
|
3 |
---
|
4 |
# SFR-SFT-LLaMA-3-8B-R
|
5 |
+
This is the SFT model for Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R.
|
6 |
+
|
7 |
+
|
8 |
+
## Citation
|
9 |
+
Please cite our techical report if you find our model is useful for your research or product.
|
10 |
+
|
11 |
+
```bibtex
|
12 |
+
@misc{dong2024rlhf,
|
13 |
+
title={RLHF Workflow: From Reward Modeling to Online RLHF},
|
14 |
+
author={Hanze Dong and Wei Xiong and Bo Pang and Haoxiang Wang and Han Zhao and Yingbo Zhou and Nan Jiang and Doyen Sahoo and Caiming Xiong and Tong Zhang},
|
15 |
+
year={2024},
|
16 |
+
eprint={2405.07863},
|
17 |
+
archivePrefix={arXiv},
|
18 |
+
primaryClass={cs.LG}
|
19 |
+
}
|
20 |
+
```
|