Hugging Face's logo

wh-zhu
/
DeepSeek-R1-TrRa-iter2-1.5B-lambda_2

Safetensors
qwen2
Model card Files
xet
Community
wh-zhu commited on
Commit
a16cc13
·
verified ·
1 Parent(s): e0e9fc0

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -1,7 +1,7 @@
1
 
2
  <h1 align="center">🛠️ ReAligner</h1>
3
  <p align="center">
4
- <a href="https://arxiv.org/abs/2503.04346"><img src="https://img.shields.io/badge/arXiv-arXiv%20Preprint-B31B1B?style=flat&logo=arxiv&logoColor=white" alt="arXiv Paper"></a>
5
  &nbsp;
6
  <a href="https://github.com/zwhong714/ReAligner"><img src="https://img.shields.io/badge/Homepage-Project%20Page-brightgreen?style=flat&logo=github" alt="Homepage"></a>
7
  &nbsp;
@@ -10,7 +10,6 @@
10
 
11
 
12
 
13
-
14
  <div>
15
  A flexible realignment framework is proposed to quantitatively control alignment during training and inference, combining Training-time Realignment (TrRa) and Inference-time Realignment (InRa).
16
 
 
1
 
2
  <h1 align="center">🛠️ ReAligner</h1>
3
  <p align="center">
4
+ <a href="https://arxiv.org/pdf/2506.12704"><img src="https://img.shields.io/badge/arXiv-arXiv%20Preprint-B31B1B?style=flat&logo=arxiv&logoColor=white" alt="arXiv Paper"></a>
5
  &nbsp;
6
  <a href="https://github.com/zwhong714/ReAligner"><img src="https://img.shields.io/badge/Homepage-Project%20Page-brightgreen?style=flat&logo=github" alt="Homepage"></a>
7
  &nbsp;
 
10
 
11
 
12
 
 
13
  <div>
14
  A flexible realignment framework is proposed to quantitatively control alignment during training and inference, combining Training-time Realignment (TrRa) and Inference-time Realignment (InRa).
15