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}
}
Downloads last month
65
Safetensors
Model size
33B params
Tensor type
BF16
·
Video Preview
loading

Model tree for jadohu/Qwen2.5-32B-MASA-efficient

Base model

Qwen/Qwen2.5-32B
Finetuned
(100)
this model

Dataset used to train jadohu/Qwen2.5-32B-MASA-efficient

Collection including jadohu/Qwen2.5-32B-MASA-efficient