skills.rest
broomva
broomvaCOMMUNITY
Explore all skills by this author →
Website𝕏@broomva_techGitHub

heretic-abliteration

Automate refusal direction removal from open-weight LLMs via directional ablation and Optuna optimization.

3|2|Updated Mar 17, 2026
Search Tags:#optimization#llm#ollama#abliteration#refusal#decensor
One-click install
npx skills add https://github.com/broomva/skills --skill heretic-abliteration
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: heretic-abliteration
Source: https://github.com/broomva/skills/tree/main/skills/models/heretic-abliteration
Command: npx skills add https://github.com/broomva/skills --skill heretic-abliteration

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, ollama, llama.cpp, heretic-llm, jinja2, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the issue of restrictive model refusals by providing a fully automated, local workflow to remove refusal directions from open-weight LLMs without requiring fine-tuning.

Core Features & Use Cases

  • Directional Ablation: Uses orthogonalization of attention and MLP projections to surgically remove refusal behaviors.
  • Optuna-TPE Optimization: Co-minimizes refusal counts and KL divergence to ensure the model remains intelligent and coherent.
  • Ollama Integration: Provides a seamless pipeline to convert abliterated HF models into GGUF format for immediate serving via the Ollama CLI.

Quick Start

Run the heretic abliteration script on your chosen model to remove refusals and prepare it for local serving.

Frequently Asked Questions about heretic-abliteration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove refusal directions from an open-weight LLM locally?▼

You can remove refusal directions locally by applying directional ablation, specifically orthogonalizing attention and MLP projections to surgically eliminate refusal behaviors without requiring fine-tuning.

How does Optuna-tuned abliteration keep a decensored model coherent?▼

Optuna-TPE optimization co-minimizes refusal counts and KL divergence during abliteration, ensuring the decensored model retains its original intelligence and coherence rather than degrading into random outputs.

What is the best way to serve an abliterated model using Ollama?▼

The best way to serve an abliterated model via Ollama is to convert the modified HF weights into GGUF format using llama.cpp tooling, then deploy the quantized model through the Ollama CLI.

Do I need a specific Python environment to run local LLM decensoring?▼

Yes, local LLM decensoring requires a Python environment with PyTorch and llama.cpp tooling installed to perform weight orthogonalization, manipulation, and subsequent GGUF conversion.

Does abliteration require fine-tuning the model weights?▼

No, abliteration does not require fine-tuning; it uses weight orthogonalization of attention and MLP projections to directly remove refusal directions from the open-weight LLM.

Related Skills

Explore More Software Engineering Skills→
jayll1303jayll1303
17

model-quantization

Quantize large language models with GGUF, GPTQ, AWQ, and bitsandbytes.

Community
Advanced
afel6afel6

gguf-quantization

Convert and quantize transformer models into GGUF format for CPU inference.

Community
Advanced
OlixIgnaciousOlixIgnacious
1

kaggle-optuna

Optimizes hyperparameters of Kaggle machine learning models using Optuna's TPE sampler for LightGBM, XGBoost, CatBoost, and ensembles.

Community
Advanced
DarkArty07DarkArty07
3

obliteratus

Remove refusal guardrails from open-weight LLMs via weight projection.

Community
Advanced