R0U5/Lethe
Model-agnostic abliteration toolkit for HuggingFace causal LMs: compute and remove refusal directions via weight orthogonalization or runtime hooks, with KL-aware Optuna optimization, quantized-model bundles, and a local web UI.
GitHub repository with 8 stars and 1 forks.
Language: Python
Topics: abliteration, ai-alignment, ai-safety, huggingface, interpretability, llm, machine-learning, nlp, pytorch, refusal-direction