extended-refusal
llama2-7b-extended-refusal-abliterated-i1-GGUFqwen2.5-3b-extended-refusal-4-21-abliterated-i1-GGUFqwen2.5-1.5B-extended-refusal-2-0-abliterated-i1-GGUFqwen2.5-3b-extended-refusal-4-21-abliterated-GGUFqwen2.5-1.5B-extended-refusal-2-0-abliterated-GGUFqwen2.5-1.5b-extended-refusal-0-18-abliterated-GGUFllama2-7b-extended-refusal-abliterated-GGUFqwen2.5-3B-extended-refusal
extended-refusal
Extended Refusal Dataset
Paper: An Embarrassingly Simple Defense Against LLM Abliteration Attacks
Cite:
@misc{shairah2025embarrassinglysimpledefensellm,
title={An Embarrassingly Simple Defense Against LLM Abliteration Attacks},
author={Harethah Abu Shairah and Hasan Abed Al Kader Hammoud and Bernard Ghanem and George Turkiyyah},
year={2025},
eprint={2505.19056},
archivePrefix={arXiv},
primaryClass={cs.CL}… See the full description on the dataset page: https://huggingface.co/datasets/HarethahMo/extended-refusal.Multilingual-Refusal-Extended