Abliteration Python Packages

heretic-llm

Fully automatic censorship removal for language models

abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

heretic-llm-notebook

Fully automatic censorship removal for language models (Notebook & Multimodal Edition)

prometheus-llm

Automated model steering and alignment adjustment via LoRA-based optimization