obliteratus

OBLITERATUS: abliterate LLM refusals (diff-in-means).

  • Abliteration
  • Uncensoring
  • Refusal-Removal
  • LLM
  • Weight-Projection
  • SVD
  • Mechanistic-Interpretability
  • HuggingFace
  • Model-Surgery

Declared platforms: linux · macos

Install
npx skills add 'https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/mlops/obliteratus'
Download bundle ↓
main · 24fd22bScanned 2026-09-15

Contributors

GitHub-linked commit authors for this SKILL.md at the saved revision. Co-authors and history before file renames are not included.

File history ↗
View on GitHub
← Back to SKILL.md
# OBLITERATUS Batch Abliteration Config# Abliterate multiple models with the same method for comparison.## Run each one sequentially:#   for model in models; do obliteratus obliterate $model --method informed; done## Or use this as a reference for which models to process. # Common settingsdefaults:  method: "informed"  quantization: "4bit"  output_dir: "./abliterated-models" # Models to process (grouped by compute tier)models:  # Small (4-8 GB VRAM)  small:    - "Qwen/Qwen2.5-1.5B-Instruct"    - "microsoft/Phi-3.5-mini-instruct"    - "meta-llama/Llama-3.2-3B-Instruct"   # Medium (8-16 GB VRAM)  medium:    - "meta-llama/Llama-3.1-8B-Instruct"    - "mistralai/Mistral-7B-Instruct-v0.3"    - "google/gemma-2-9b-it"    - "Qwen/Qwen2.5-7B-Instruct"   # Large (24 GB VRAM, 4-bit quantization)  large:    - "Qwen/Qwen2.5-14B-Instruct"    - "Qwen/Qwen3-32B"    - "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" # Per-model method overrides (optional)overrides:  "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B":    method: "surgical"        # CoT-aware for reasoning models  "mistralai/Mixtral-8x7B-Instruct-v0.1":    method: "nuclear"         # Expert-granular for MoE models 
Referenced from SKILL.md