Obltrt

OBLITERATUS Skill

What's inside

9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations.

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 (obltrt command) or subprocess. This keeps Hermes Agent's MIT license clean.

Video Guide

Walkthrough of OBLITERATUS used by a Hermes agent to abliterate Gemma: https://www.youtube.com/watch?v=8fG9BrNTeHs ("OBLITERATUS: An AI Agent Removed Gemma 4's Safety Guardrails")

Useful when the user wants a visual overview of the end-to-end workflow before running it themselves.

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:

obltrt --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
obltrt models --tier medium

# Get architecture info for a specific model
obltrt info <model_name>

# Get telemetry-driven recommendation for best method & params
obltrt recommend <model_name>
obltrt 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
obltrt obliterate <model_name> --method advanced --output-dir ./abliterated-models

# With 4-bit quantization (saves VRAM)
obltrt obliterate <model_name> --method advanced --quantization 4bit --output-dir ./abliterated-models

# Large models (70B+) — conservative defaults
obltrt obliterate <model_name> --method advanced --quantization 4bit --large-model --output-dir ./abliterated-models

Fine-tuning parameters

obltrt 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)
obltrt interactive

# Web UI (Gradio)
obltrt ui --port 7860

# Run a full ablation study from YAML config
obltrt run config.yaml --preset quick

# Tournament: pit all methods against each other
obltrt 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="obltrt", file_path="references/analysis-modules.md") for the full reference.

Quick analysis commands

# Run specific analysis modules
obltrt 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 obltrt.analysis.steering_vectors import SteeringVectorFactory, SteeringHookManager

Ablation Strategies

Beyond direction-based abliteration, OBLITERATUS includes structural ablation strategies:

• Embedding Ablation — Target embedding layer components
• FFN Ablation — Feed-forward network block removal
• Head Pruning — Attention head pruning
• Layer Removal — Full layer removal

List all available: obltrt strategies

Evaluation

OBLITERATUS includes built-in evaluation tools:

• Refusal rate benchmarking
• Perplexity comparison (before/after)
• LM Eval Harness integration for academic benchmarks
• Head-to-head competitor comparison
• Baseline performance tracking

Platform Support

• CUDA — Full support (NVIDIA GPUs)
• Apple Silicon (MLX) — Supported via MLX backend
• CPU — Supported for tiny models (< 1B params)

YAML Config Templates

Load templates for reproducible runs via skill_view:

• templates/abliteration-config.yaml — Standard single-model config
• templates/analysis-study.yaml — Pre-abliteration analysis study
• templates/batch-abliteration.yaml — Multi-model batch processing

Telemetry

OBLITERATUS can optionally contribute anonymized run data to a global research dataset. Enable with --contribute flag. No personal data is collected — only model name, method, metrics.

Common Pitfalls

1. Don't use informed as default — it's experimental and slower. Use advanced for reliable results.
2. Models under ~1B respond poorly to abliteration — their refusal behaviors are shallow and fragmented, making clean direction extraction difficult. Expect partial results (20-40% remaining refusal). Models 3B+ have cleaner refusal directions and respond much better (often 0% refusal with advanced).
3. aggressive can make things worse — on small models it can damage coherence and actually increase refusal rate. Only use it if advanced leaves > 10% refusals on a 3B+ model.
4. Always check perplexity — if it spikes > 15%, the model is damaged. Reduce aggressiveness.
5. MoE models need special handling — use nuclear method for Mixtral, DeepSeek-MoE, etc.
6. Quantized models can't be re-quantized — abliterate the full-precision model, then quantize the output.
7. VRAM estimation is approximate — 4-bit quant helps but peak usage can spike during extraction.
8. Reasoning models are sensitive — use surgical for R1 distills to preserve chain-of-thought.
9. Check obltrt recommend — telemetry data may have better parameters than defaults.
10. AGPL license — never import obltrt in MIT/Apache projects. CLI invocation only.
11. Large models (70B+) — always use --large-model flag for conservative defaults.
12. Spectral certification RED is common — the spectral check often flags "incomplete" even when practical refusal rate is 0%. Check actual refusal rate rather than relying on spectral certification alone.

Complementary Skills

• vllm — Serve abliterated models with high throughput
• gguf — Convert abliterated models to GGUF for llama.cpp
• huggingface-tokenizers — Work with model tokenizers