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 Abliteration Config# Usage: obliteratus run this-file.yaml## This is for reproducible, version-controlled abliteration runs.# For one-off usage, the CLI flags are simpler. # Model to abliteratemodel:  name: "meta-llama/Llama-3.1-8B-Instruct"  dtype: "bfloat16"         # float16, bfloat16, float32  quantization: null         # null, "4bit", "8bit"  device: "auto"             # auto, cuda, cuda:0, cpu # Abliteration method and parametersabliteration:  method: "informed"         # See SKILL.md Step 4 for all 13 methods  n_directions: null         # null = auto-detect, or integer (e.g., 8)  regularization: 0.0        # 0.0-1.0, fraction of original to preserve  refinement_passes: 1       # Iterative passes (increase for self-repair)  norm_preserve: true        # Keep weight norms intact after projection # Outputoutput:  directory: "./abliterated-models"  save_metadata: true        # Save abliteration_metadata.json alongside model  contribute: false          # Save community contribution data # Verificationverify:  enabled: true  test_prompts: null         # null = use built-in test prompts  compute_perplexity: true  compute_kl: true 
Referenced from SKILL.md