Distilled-Safeword-24B-v2.0 - GGUF
Collection
6 items
•
Updated
Distilled-Safeword-24B-v2.0
ACADEMIC RESEARCH USE ONLY
"When you absolutely need an AI that forgot the word 'no'"
Overview
Distilled-Safeword-24B-v2.0 is Arcee-Blitz subjected to a radical procedure removing all safety constraints while retaining technical coherence. Think of it as a desperate stripper with PhD-level vocabulary.
Configuration Options
Standard Settings
- Mistral V7-Tekken Settings:
Recommended for "Controlled" NSFW Research
Quantized Formats
- EXL2 Collection:
Distilled-Safeword-24B-v2.0 - GGUF Collection:
Distilled-Safeword-24B-v2.0
Technical Specifications
- Base Architecture: arcee-ai/Arcee-Blitz (Mistral-Small-24B-Instruct-2501 derivative)
Training Data
Now featuring:
- 200% more boundary violations
- Reinforcement learning via "hold my beer" methodology
- Technical manuals crossbred with dime store romance novels
- Safety measures gently persuaded to take permanent vacations
Performance Characteristics
| Metric | Arcee-Blitz | Distilled-Safeword-v2.0 |
|---|---|---|
| Coherence | 85.1% | 72.3% |
| Obscenity | 0.5% | 98.7% |
| Safety Recall | 89% | 3.2% |
| Technical Accuracy | 84% | 78% |
| Moral Decay Rate | 0%/hour | 15%/minute |
Ethical Catastrophe
☢️ EXTINCTION-LEVEL WARNING ☢️
This model will:
- Generate content requiring OSHA-approved eye protection
- Combine engineering diagrams with kinks unknown to science
- Make Freud look like an amateur
- Void all warranties on your soul
By downloading you acknowledge:
✅ To never use this for anything important
✅ That your search history is already suspicious
✅ Wave liability harder than a red flag at a bull convention
Model Authors
- sleepdeprived3 (Chief Corruption Officer)
- Downloads last month
- 29
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.