Downloads · 30 days
13
12% of all-time downloads
Qwen2.5-32B-MASA-efficient
jadohu/Qwen2.5-32B-MASA-efficient
Qwen2.5-32B-MASA-efficient is a reinforcement learning model from jadohu. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains the model for Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning.
All-time downloads
109
Public
Parameters
32.8B
65.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors65.5 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Nov 25, 2025
- Updated
- Nov 26, 2025
- SHA
- eb6f2ff7
Base models
Model card
From the Hugging Face model README
Description
This repository contains the model for Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning.
Official Implementation
https://github.com/akatigre/MASA-RL
Citation
@article{kim2025meta,
title={Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning},
author={Kim, Yoonjeon and Jang, Doohyuk and Yang, Eunho},
journal={arXiv preprint arXiv:2510.03259},
year={2025}
}
- Task
- Reinforcement Learning
- Type
- qwen2
- License
- apache-2.0
- Created
- Nov 25, 2025
- Updated
- Nov 26, 2025