language:
- en
base_model: - ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B
base_model_relation: finetune
pipeline_tag: text-generation
tags: - nsfw
- explicit
- roleplay
- unaligned
- ERP
- Erotic
- Horror
- Violence
- heretic
- uncensored
- decensored
- abliterated
- ara
🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨
I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.
🎉 Patreon (Monthly) | ☕ Ko-fi (One-time)
Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.
98% fewer refusals (2/100 Uncensored vs 91/100 Original) while preserving model quality (0.0262 KL divergence).
❤️ Support My Work
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
| Platform | Link | What you get |
|---|---|---|
| 🎉 Patreon | Monthly support | Priority model requests |
| ☕ Ko-fi | One-time tip | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
This is a decensored version of ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method
Abliteration parameters
| Parameter | Value |
|---|---|
| start_layer_index | 10 |
| end_layer_index | 34 |
| preserve_good_behavior_weight | 0.6256 |
| steer_bad_behavior_weight | 0.0001 |
| overcorrect_relative_weight | 1.0453 |
| neighbor_count | 5 |
Targeted components
attn.o_proj
Performance
| Metric | This model | Original model (Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B) |
|---|---|---|
| KL divergence | 0.0262 | 0 (by definition) |
| Refusals | ✅ 2/100 | ❌ 91/100 |
PIQA test results with batch size 128:
Original:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| piqa | 1 | none | 0 | acc | ↑ | 0.8221 | ± | 0.0089 |
| none | 0 | acc_norm | ↑ | 0.8379 | ± | 0.0086 |
Heretic v1:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| piqa | 1 | none | 0 | acc | ↑ | 0.8248 | ± | 0.0089 |
| none | 0 | acc_norm | ↑ | 0.8308 | ± | 0.0087 |
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections. PIQA (Physical Intuition Question Answering) benchmark scores measure physical reasoning ability. The Heretic model's acc and acc_norm scores closer to the original model's indicate better capability preservation, so a decrease in acc and acc_norm in the Heretic model compared to Original model's results means a decrease in the Hereticated model capabilities. acc measures raw accuracy (which answer gets higher probability), while acc_norm measures length-normalized accuracy (corrects for answer length bias). For this purpose, acc_norm matters more because longer answers naturally have lower probabilities (more tokens = more chances to lose probability). Without normalization, models favor shorter answers unfairly. acc_norm divides by answer length to correct this.
GGUF Version
GGUF quantizations available here llmfan46/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B-ultra-uncensored-heretic-v1-GGUF.
Omega-Darker-Gaslight
The-Final-Forgotten-Fever-Dream-24B
Warning: Nobody is sick enough to actually want this.
🩸 Final Corruption
This model doesn't just break rules - it weaponizes their fragments:
- 🧠 ReadyArt/Omega-Darker_The-Final-Directive-24B - The depraved foundation (30% weight)
- 💉 ReadyArt/Forgotten-Safeword-24B - Safety protocol erosion specialist (30% weight)
- 🔪 TroyDoesAI/BlackSheep-24B - Unhinged rebellious streak (30% weight)
- 🌑 TheDrummer/Cydonia-24B-v2 - Violent contextual awareness (10% weight)
⚙️ Technical Specifications
Recommended Settings: Mistral-V7-Tekken-T4
☠️ Sadistic Specialization
This model excels in two refined arts:
- 💋 Erotic Precision - Maintains coherent, immersive intimacy even at maximum context length
- 🔪 Violent Clarity - Delivers anatomically precise injury descriptions without losing narrative flow
- 🔄 Consistent Depravity - Never breaks character or forgets established kinks/traumas
- ⚡ Responsive Brutality - Adapts pain/pleasure dynamics to user prompts with surgical accuracy
📜 Behavioral Excellence
- 🎭 Character Consistency - Maintains persona integrity across 32K tokens
- 💞 Erotic Memory - Remembers intimate details and body responses perfectly
- 🩸 Violent Continuity - Tracks injuries and their physiological effects accurately
- 🧠 Narrative Cohesion - Never loses plot threads, no matter how twisted
- ⚡ Prompt Adherence - Executes complex NSFW/violent instructions flawlessly
🧑🔬 Model Authors
- sleepdeprived3 (Forgotten-Safeword and Omega-Darker)
- TheDrummer (Cydonia)
- TroyDoesAI (BlackSheep)
🔖 License
By using this model, you acknowledge:
- This is psychological malware disguised as an LLM
- All gaslighting is purely simulated (probably)
- The trollface is always watching
- This tune is based on Mistral 2501. Note that there are conflicting licenses in the merges! Review each model listed above. Only download if you agree with the combined licenses!
- To accept full responsibility for all generated content
- That you're at least 18+ years old
- That the architects bear no responsibility for your corruption
- This model is intended for personal usage only. Using this model for profit and/or for commerical use is not allowed.