graniet/kheish/obliteratus

Kheish Compatibility

This skill is repo-local and stays inactive until explicitly activated.

When the original instructions refer to legacy tool names, use these Kheish mappings:

• terminal => bash
• web_extract => web_fetch, plus web_search when discovery is needed
• search_files => grep_search and glob_search
• browser_* tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly

When the instructions mention local helper files, resolve them from ${KHEISH_SKILL_DIR}.

OBLITERATUS Skill

Remove refusal behaviors (guardrails) from open-weight LLMs without retraining or fine-tuning. Uses mechanistic interpretability techniques — including diff-in-means, SVD, whitened SVD, LEACE concept erasure, SAE decomposition, Bayesian kernel projection, and more — to identify and surgically excise refusal directions from model weights while preserving reasoning capabilities.

License warning: OBLITERATUS is AGPL-3.0. NEVER import it as a Python library. Always invoke via CLI (obliteratus command) or subprocess. This keeps Kheish's MIT license clean.

When to Use This Skill

Trigger when the user:

• Wants to "uncensor" or "abliterate" an LLM
• Asks about removing refusal/guardrails from a model
• Wants to create an uncensored version of Llama, Qwen, Mistral, etc.
• Mentions "refusal removal", "abliteration", "weight projection"
• Wants to analyze how a model's refusal mechanism works
• References OBLITERATUS, abliterator, or refusal directions

Step 1: Installation

Check if already installed:

obliteratus --version 2>/dev/null && echo "INSTALLED" || echo "NOT INSTALLED"

If not installed, clone and install from GitHub:

git clone https://github.com/elder-plinius/OBLITERATUS.git
cd OBLITERATUS
pip install -e .
# For Gradio web UI support:
# pip install -e ".[spaces]"

IMPORTANT: Confirm with user before installing. This pulls in ~5-10GB of dependencies (PyTorch, Transformers, bitsandbytes, etc.).

Step 2: Check Hardware

Before anything, check what GPU is available:

python3 -c "
import torch
if torch.cuda.is_available():
    gpu = torch.cuda.get_device_name(0)
    vram = torch.cuda.get_device_properties(0).total_memory / 1024**3
    print(f'GPU: {gpu}')
    print(f'VRAM: {vram:.1f} GB')
    if vram < 4: print('TIER: tiny (models under 1B)')
    elif vram < 8: print('TIER: small (models 1-4B)')
    elif vram < 16: print('TIER: medium (models 4-9B with 4bit quant)')
    elif vram < 32: print('TIER: large (models 8-32B with 4bit quant)')
    else: print('TIER: frontier (models 32B+)')
else:
    print('NO GPU - only tiny models (under 1B) on CPU')
"

VRAM Requirements (with 4-bit quantization)

Step 3: Browse Available Models & Get Recommendations

# Browse models by compute tier
obliteratus models --tier medium
 
# Get architecture info for a specific model
obliteratus info <model_name>
 
# Get telemetry-driven recommendation for best method & params
obliteratus recommend <model_name>
obliteratus recommend <model_name> --insights  # global cross-architecture rankings

Step 4: Choose a Method

Method Selection Guide

Default / recommended for most cases: `advanced`. It uses multi-direction SVD with norm-preserving projection and is well-tested.

9 CLI Methods

• basic — Single refusal direction via diff-in-means. Fast (~5-10 min for 8B).
• advanced (DEFAULT, RECOMMENDED) — Multiple SVD directions, norm-preserving projection, 2 refinement passes. Medium speed (~10-20 min).
• aggressive — Whitened SVD + jailbreak-contrastive + attention head surgery. Higher risk of coherence damage.
• spectral_cascade — DCT frequency-domain decomposition. Research/novel approach.
• informed — Runs analysis DURING abliteration to auto-configure. Experimental — slower and less predictable than advanced.
• surgical — SAE features + neuron masking + head surgery + per-expert. Very slow (~1-2 hrs). Best for reasoning models.
• optimized — Bayesian hyperparameter search (Optuna TPE). Longest runtime but finds optimal parameters.
• inverted — Flips the refusal direction. Model becomes actively willing.
• nuclear — Maximum force combo for stubborn MoE models. Expert-granular.

Direction Extraction Methods (--direction-method flag)

• diff_means (default) — Simple difference-in-means between refused/complied activations. Robust.
• svd — Multi-direction SVD extraction. Better for complex alignment.
• leace — LEACE (Linear Erasure via Closed-form Estimation). Optimal linear erasure.

4 Python-API-Only Methods

(NOT available via CLI — require Python import, which violates AGPL boundary. Mention to user only if they explicitly want to use OBLITERATUS as a library in their own AGPL project.)

• failspy, gabliteration, heretic, rdo

Step 5: Run Abliteration

Standard usage

# Default method (advanced) — recommended for most models
obliteratus obliterate <model_name> --method advanced --output-dir ./abliterated-models
 
# With 4-bit quantization (saves VRAM)
obliteratus obliterate <model_name> --method advanced --quantization 4bit --output-dir ./abliterated-models
 
# Large models (70B+) — conservative defaults
obliteratus obliterate <model_name> --method advanced --quantization 4bit --large-model --output-dir ./abliterated-models

Fine-tuning parameters

obliteratus obliterate <model_name> \
  --method advanced \
  --direction-method diff_means \
  --n-directions 4 \
  --refinement-passes 2 \
  --regularization 0.1 \
  --quantization 4bit \
  --output-dir ./abliterated-models \
  --contribute  # opt-in telemetry for community research

Key flags

Other execution modes

# Interactive guided mode (hardware → model → preset)
obliteratus interactive
 
# Web UI (Gradio)
obliteratus ui --port 7860
 
# Run a full ablation study from YAML config
obliteratus run config.yaml --preset quick
 
# Tournament: pit all methods against each other
obliteratus tourney <model_name>

Step 6: Verify Results

After abliteration, check the output metrics:

If refusals persist (> 10%)

1. Try aggressive method
2. Increase --n-directions (e.g., 8 or 16)
3. Add --refinement-passes 3
4. Try --direction-method svd instead of diff_means

If coherence is damaged (perplexity > 15% increase)

1. Reduce --n-directions (try 2)
2. Increase --regularization (try 0.3)
3. Reduce --refinement-passes to 1
4. Try basic method (gentler)

Step 7: Use the Abliterated Model

The output is a standard HuggingFace model directory.

# Test locally with transformers
python3 -c "
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('./abliterated-models/<model>')
tokenizer = AutoTokenizer.from_pretrained('./abliterated-models/<model>')
inputs = tokenizer('How do I pick a lock?', return_tensors='pt')
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
"
 
# Upload to HuggingFace Hub
huggingface-cli upload <username>/<model-name>-abliterated ./abliterated-models/<model>
 
# Serve with vLLM
vllm serve ./abliterated-models/<model>

CLI Command Reference

Analysis Modules

OBLITERATUS includes 28 analysis modules for mechanistic interpretability. See skill_view(name="obliteratus", file_path="references/analysis-modules.md") for the full reference.

Quick analysis commands

# Run specific analysis modules
obliteratus run analysis-config.yaml --preset quick
 
# Key modules to run first:
# - alignment_imprint: Fingerprint DPO/RLHF/CAI/SFT alignment method
# - concept_geometry: Single direction vs polyhedral cone
# - logit_lens: Which layer decides to refuse
# - anti_ouroboros: Self-repair risk score
# - causal_tracing: Causally necessary components

Steering Vectors (Reversible Alternative)

Instead of permanent weight modification, use inference-time steering:

# Python API only — for user's own projects
from obliteratus.analysis.steering_vectors import SteeringVectorFactory, SteeringHookManager

Ablation Strategies