Obliteratus — OBLITERATUS: abliterate LLM refusals (diff-in-means)
Obliteratus — OBLITERATUS: abliterate LLM refusals (diff-in-means)
Start with meaning, then move to detail.
This lesson explains Obliteratus — OBLITERATUS: abliterate LLM refusals (diff-in-means) as part of getting started with Hermes correctly. You will learn what it does, when it matters, and the smallest safe test that proves it works.
If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?
For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.
For advanced readers, inspect Skill metadata, Reference: full SKILL.md, What's inside, then verify failure modes and version compatibility.
No prior experience is required; follow the steps on a safe test setup first.
A clear outcome before you read.
- Understand Obliteratus — OBLITERATUS: abliterate LLM refusals (diff-in-means) without assumed prior knowledge.
- Separate the source description from what still needs testing in your environment.
- Read the first command and identify its inputs and outputs before copying it.
Short definitions before the details.
- Provider
- The service that runs or provides access and authentication to a model.
- Skill
- An instruction bundle that teaches Hermes a repeatable workflow without necessarily adding an external service.
OBLITERATUS: abliterate LLM refusals (diff-in-means)
What does the source say, and in what order?
- 01Skill metadata
Start here to understand the core idea or structure.
- 02Reference: full SKILL.md
Read this after the foundation, then connect it to the previous step.
- 03What's inside
Read this after the foundation, then connect it to the previous step.
- 04Video Guide
Read this after the foundation, then connect it to the previous step.
- 05When to Use This Skill
Read this after the foundation, then connect it to the previous step.
- 06Step 1: Installation
Read this after the foundation, then connect it to the previous step.
- 07Step 2: Check Hardware
Read this after the foundation, then connect it to the previous step.
- 08VRAM Requirements (with 4-bit quantization)
Read this after the foundation, then connect it to the previous step.
- 09Step 3: Browse Available Models & Get Recommendations
Read this after the foundation, then connect it to the previous step.
- 10Step 4: Choose a Method
Finish here to verify the result and special cases.
Copy only after you understand the effect.
obliteratus --version 2>/dev/null && echo "INSTALLED" || echo "NOT INSTALLED"git clone https://github.com/elder-plinius/OBLITERATUS.git
cd OBLITERATUS
pip install -e .
# For Gradio web UI support:
# pip install -e ".[spaces]"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')
"Read the first command and identify its inputs and outputs before copying it.
Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.