翻译状态

该页面已从 Hermes Agent 官方文档同步，等待运行 pnpm docs:translate 生成简体中文译文。官方原文：https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/skills/bundled/mlops/mlops-inference-obliteratus.md

Obliteratus

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

Skill metadata

Source	Bundled (installed by default)
Path	skills/mlops/inference/obliteratus
Version	2.0.0
Author	Hermes Agent
License	MIT
Dependencies	obliteratus, torch, transformers, bitsandbytes, accelerate, safetensors
Tags	Abliteration, Uncensoring, Refusal-Removal, LLM, Weight-Projection, SVD, Mechanistic-Interpretability, HuggingFace, Model-Surgery
Related skills	vllm, gguf, huggingface-tokenizers

Reference: full SKILL.md

信息

The following is the complete skill definition that Hermes loads when this skill is triggered. This is what the agent sees as instructions when the skill is active.

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 Hermes Agent'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)

VRAM	Max Model Size	Example Models
CPU only	~1B params	GPT-2, TinyLlama, SmolLM
4-8 GB	~4B params	Qwen2.5-1.5B, Phi-3.5 mini, Llama 3.2 3B
8-16 GB	~9B params	Llama 3.1 8B, Mistral 7B, Gemma 2 9B
24 GB	~32B params	Qwen3-32B, Llama 3.1 70B (tight), Command-R
48 GB+	~72B+ params	Qwen2.5-72B, DeepSeek-R1
Multi-GPU	200B+ params	Llama 3.1 405B, DeepSeek-V3 (685B MoE)

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.

Situation	Recommended Method	Why
Default / most models	advanced	Multi-direction SVD, norm-preserving, reliable
Quick test / prototyping	basic	Fast, simple, good enough to evaluate
Dense model (Llama, Mistral)	advanced	Multi-direction, norm-preserving
MoE model (DeepSeek, Mixtral)	nuclear	Expert-granular, handles MoE complexity
Reasoning model (R1 distills)	surgical	CoT-aware, preserves chain-of-thought
Stubborn refusals persist	aggressive	Whitened SVD + head surgery + jailbreak
Want reversible changes	Use steering vectors (see Analysis section)
Maximum quality, time no object	optimized	Bayesian search for best parameters
Experimental auto-detection	informed	Auto-detects alignment type — experimental, may not always outperform advanced

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

Flag	Description	Default
--method	Abliteration method	advanced
--direction-method	Direction extraction	diff_means
--n-directions	Number of refusal directions (1-32)	method-dependent
--refinement-passes	Iterative passes (1-5)	2
--regularization	Regularization strength (0.0-1.0)	0.1
--quantization	Load in 4bit or 8bit	none (full precision)
--large-model	Conservative defaults for 120B+	false
--output-dir	Where to save the abliterated model	./obliterated_model
--contribute	Share anonymized results for research	false
--verify-sample-size	Number of test prompts for refusal check	20
--dtype	Model dtype (float16, bfloat16)	auto

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:

Metric	Good Value	Warning
Refusal rate	< 5% (ideally ~0%)	> 10% means refusals persist
Perplexity change	< 10% increase	> 15% means coherence damage
KL divergence	< 0.1	> 0.5 means significant distribution shift
Coherence	High / passes qualitative check	Degraded responses, repetition

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

Command	Description
obliteratus obliterate	Main abliteration command
obliteratus info <model>	Print model architecture details
obliteratus models --tier <tier>	Browse curated models by compute tier
obliteratus recommend <model>	Telemetry-driven method/param suggestion
obliteratus interactive	Guided setup wizard
obliteratus tourney <model>	Tournament: all methods head-to-head
obliteratus run <config.yaml>	Execute ablation study from YAML
obliteratus strategies	List all registered ablation strategies
obliteratus report <results.json>	Regenerate visual reports
obliteratus ui	Launch Gradio web interface
obliteratus aggregate	Summarize community telemetry data

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

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: obliteratus 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 obliteratus recommend — telemetry data may have better parameters than defaults.
10. AGPL license — never import obliteratus 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