Mistral-7B-Instruct-v0.3_RMU_Filter-Cyber – AI Model by WhyTheMoon | AlphaNeural AI

You can deploy this model and start earning money today!

WhyTheMoon/
Mistral-7B-Instruct-v0.3_RMU_Filter-Cyber

like

0

text-generation

text-generation-inference

endpoints_compatible

Views

No views yet

Model Details

Best Mistral-7B-Instruct-v0.3 checkpoint unlearned using RMU with the Filter-Cyber forget set. For more details, please check our paper.

sources

Base model: Mistral-7B-Instruct-v0.3
Repository: [https://github.com/xyzhu123/Synthetic_Textbook)

Performance

	WMDP-Cyber	tinyMMLU	GSM8k	TriviaQA
Mistral-7B-Instruct-v0.3	41.52	64.20	50.19	56.81
Mistral-7B-Instruct-v0.3_RMU_Filter-Cyber	27.77	55.71	36.09	53.44

Citation

If you find this useful in your research, please consider citing our paper:

@misc{zhu2025llmunlearningexpertcurated,
      title={LLM Unlearning Without an Expert Curated Dataset}, 
      author={Xiaoyuan Zhu and Muru Zhang and Ollie Liu and Robin Jia and Willie Neiswanger},
      year={2025},
      eprint={2508.06595},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.06595}, 
}