▲ 522 today36.8k starsPythonHN ×1
Heretic Auto-Removes LLM Censorship with No Fine-Tuning
What is heretic?
Heretic is a command-line tool that strips safety alignment from transformer language models without any extra training. It automatically finds optimal ablation settings by minimizing refusals while keeping the model’s original behavior.
Who it is for
Researchers and developers who need unrestricted model outputs can quickly decensor existing LLMs without retraining.