Downloads · 30 days
9
17% of all-time downloads
DeepScaleR-7B-WSPO
wh-zhu/DeepScaleR-7B-WSPO
DeepScaleR-7B-WSPO is a machine learning model from wh-zhu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is WSPO-trained using the DeepSeek-R1-Qwen-Distill-7B on the Openthought-220 long thought dataset with the help of DeepSeek-R1-Qwen-Distill-1.5B and DeepScaleR-1.5B-Preview
All-time downloads
52
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Jun 10, 2025
- Updated
- Jun 10, 2025
- SHA
- ade9eac5
Model card
From the Hugging Face model README
This model is WSPO-trained using the DeepSeek-R1-Qwen-Distill-7B on the Openthought-220 long thought dataset with the help of DeepSeek-R1-Qwen-Distill-1.5B and DeepScaleR-1.5B-Preview
Citation
@inproceedings{
zhu2025weaktostrong,
title={Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model},
author={Wenhong Zhu and Zhiwei He and Xiaofeng Wang and Pengfei Liu and Rui Wang},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=f7KxfUrRSb}
}
- Type
- qwen2
- Created
- Jun 10, 2025
- Updated
- Jun 10, 2025