p-e-w/heretic

README 발췌

Heretic: Fully automatic censorship removal for language models Heretic is a tool that removes censorship (aka "safety alignment") from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration" (Arditi et al. 2024, Lai 2025 (1, 2)), with a TPE-based parameter optimizer powered by Optuna. This approach enables Heretic to work completely automatically. Heretic finds high-quality abliteration parameters by co-minimizing the number of refusals and the KL divergence from the original model. This results in a decensored model that retains as much of the original model's intelligence as possible. Using Heretic does not require an understanding of transformer internals. In fact, anyone who knows how to run a command-line program can use Heretic to decensor language models. Heretic supports most dense models, including many multimodal models, several different MoE architectures, and even some hybrid models like Qwen3.5. Pure state-space models and certain other research architectures are not yet supported out of the box.   Running unsupervised with the default configuration, Heretic ca…

GitHub README의 앞부분을 저장된 그대로 최대 1,200자까지 옮겼습니다. 마크다운 서식은 표시하지 않습니다.