p-e-w/heretic

Health v2 · maintenance only

Adoption not part of the score

28157 stars · 3055 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Heretic is a command-line tool that automatically removes censorship (safety alignment) from transformer-based language models using directional ablation (abliteration) combined with Optuna-based TPE parameter optimization. It requires no knowledge of transformer internals and produces decensored models that minimize refusals while preserving the original model's behavior via KL divergence minimization.

Use cases

• remove censorship from a language model
• abliterate an LLM automatically
• decensor gemma or qwen models
• make an LLM follow instructions without refusals
• strip safety alignment from a transformer model
• produce an abliterated version of a hugging face model
• optimize abliteration parameters without manual tuning

When to choose

• you want to remove refusals from a dense, MoE, or multimodal transformer model without post-training
• you lack expertise in transformer internals but can run a CLI program
• you want decensoring quality comparable to expert manual abliteration
• you want to minimize KL divergence from the original model while removing refusals

When to avoid

• you need to modify pure state-space models or unsupported research architectures
• you want to add new capabilities via fine-tuning rather than remove refusals
• you need a tool for safety alignment or content moderation rather than its removal
• your use case requires compliance with model license terms that prohibit modification

Facets

cli-tool · maturity active

llm-inference machine-learning cli large-language-models artificial-intelligence developer-tools python windows cli abliteration decensoring safety-alignment-removal directional-ablation optuna transformer-models model-modification linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="p-e-w/heretic")