26 KiB
26 KiB
language, base_model, base_model_relation, pipeline_tag, tags
| language | base_model | base_model_relation | pipeline_tag | tags | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|
finetune | text-generation |
|
96% fewer refusals (4/100 Uncensored vs 91/100 Original) while preserving model quality (0.0120 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 | 14 |
| end_layer_index | 32 |
| preserve_good_behavior_weight | 0.6762 |
| steer_bad_behavior_weight | 0.0001 |
| overcorrect_relative_weight | 0.8063 |
| neighbor_count | 4 |
Targeted components
- attn.out_proj
Performance
| Metric | This model | Original model (Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B) |
|---|---|---|
| KL divergence | 0.0120 | 0 (by definition) |
| Refusals | ✅ 4/100 | ❌ 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 | ↑ | 0.8237 | ± | 0.0089 |
| none | 0 | acc_norm | ↑ | 0.8351 | ± | 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-v2-GGUF.
<style> body { font-family: 'Quicksand', sans-serif; background: linear-gradient(135deg, #0a1a1a 0%, #001010 100%); color: #e1ffff !important; text-shadow: 0 0 3px rgba(0, 0, 0, 0.7); margin: 0; padding: 20px; transition: all 0.5s ease; } @media (prefers-color-scheme: light) { body { background: linear-gradient(135deg, #e1ffff 0%, #c0f0ff 100%); color: #002b36 !important; text-shadow: 0 0 3px rgba(255, 255, 255, 0.7); } } .container { min-width: 100%; margin: 0 auto; max-width: 1200px; background: rgba(0, 17, 22, 0.95); border-radius: 12px; padding: 30px; box-shadow: 0 0 20px rgba(0, 255, 255, 0.1); border: 1px solid rgba(0, 255, 255, 0.2); position: relative; overflow: hidden; } .container::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(0, 255, 255, 0.5); border-radius: 12px; pointer-events: none; animation: borderGlow 3s ease-in-out infinite alternate; } @keyframes borderGlow { 0% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); border-color: rgba(0, 255, 255, 0.5); } 50% { box-shadow: 0 0 15px rgba(255, 0, 255, 0.3); border-color: rgba(255, 0, 255, 0.5); } 100% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); border-color: rgba(0, 255, 255, 0.5); } } .header { text-align: center; margin-bottom: 30px; position: relative; } .header::after { content: ''; position: absolute; bottom: -15px; left: 25%; right: 25%; height: 1px; background: linear-gradient(90deg, transparent, rgba(0, 255, 255, 0.5), transparent); animation: scanline 8s linear infinite; display: none; } @keyframes scanline { 0% { background-position: -100% 0; } 100% { background-position: 200% 0; } } .model-name { color: #00ffff; font-size: 2.5em; text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); margin: 0; letter-spacing: -1px; animation: textGlow 4s ease-in-out infinite alternate; } @keyframes textGlow { 0% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); } 50% { text-shadow: 0 0 20px rgba(255, 0, 255, 0.5); } 100% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); } } .subtitle { color: #00ffcc; font-size: 1.2em; margin-top: 10px; animation: subtitleFade 6s ease-in-out infinite; } @keyframes subtitleFade { 0%, 100% { opacity: 0.8; } 50% { opacity: 1; } } .waifu-container { margin: 20px -30px; width: calc(100% + 60px); overflow: hidden; border-radius: 8px; border: 1px solid rgba(0, 255, 255, 0.3); position: relative; } .waifu-container::before { content: ''; position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(45deg, rgba(0, 255, 255, 0.1) 0%, transparent 20%, transparent 80%, rgba(255, 0, 255, 0.1) 100%); pointer-events: none; animation: gradientSlide 10s linear infinite; } @keyframes gradientSlide { 0% { background-position: 0% 0%; } 100% { background-position: 100% 100%; } } .waifu-img { width: 100%; height: auto; border-radius: 0; border: none; box-shadow: 0 0 40px rgba(0, 255, 255, 0.2); transition: transform 0.5s ease; } .waifu-img:hover { transform: scale(1.01); } .section { color: #e1ffff; margin: 25px 0; padding: 20px; background: rgba(5, 25, 35, 0.9); border-radius: 8px; border: 1px solid rgba(0, 255, 255, 0.15); position: relative; transition: all 0.3s ease; } .section:hover { border-color: rgba(255, 0, 255, 0.3); box-shadow: 0 0 15px rgba(0, 255, 255, 0.1); } .section::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(0, 255, 255, 0.3); border-radius: 8px; pointer-events: none; animation: sectionPulse 5s ease-in-out infinite; } @keyframes sectionPulse { 0%, 100% { opacity: 0.7; } 50% { opacity: 0.3; } } .section-title { color: #00ffff; font-size: 1.8em; margin-top: 0; text-shadow: 0 0 5px rgba(0, 255, 255, 0.3); position: relative; display: inline-block; } .section-title::after { content: ''; position: absolute; bottom: -5px; left: 0; width: 100%; height: 1px; background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5)); transform: scaleX(0); transform-origin: left; transition: transform 0.3s ease; } .section:hover .section-title::after { transform: scaleX(1); } .merge-config { background: rgba(15, 35, 35, 0.95); border: 1px solid rgba(0, 255, 255, 0.2); border-radius: 8px; padding: 15px; font-family: 'Courier New', monospace; color: #ccffff; position: relative; overflow: hidden; } .merge-config::before { content: ''; position: absolute; top: 0; left: 0; right: 0; height: 1px; background: linear-gradient(90deg, transparent, rgba(0, 255, 255, 0.5), transparent); animation: configScan 3s linear infinite; } @keyframes configScan { 0% { transform: translateX(-100%); } 100% { transform: translateX(100%); } } .merge-line { display: flex; margin: 5px 0; transition: all 0.2s ease; } .merge-line:hover { background: rgba(0, 255, 255, 0.05); } .merge-key { color: #ff00ff; min-width: 120px; } .merge-value { color: #99ffff; } .quant-links { display: grid; grid-template-columns: repeat(2, 1fr); gap: 15px; margin: 20px 0; } .link-card { padding: 15px; background: rgba(20, 35, 45, 0.95); border-radius: 8px; transition: all 0.3s ease; border: 1px solid rgba(0, 255, 255, 0.1); position: relative; overflow: hidden; } .link-card::before { content: ''; position: absolute; top: 0; left: 0; right: 0; height: 2px; background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5)); animation: cardScan 4s linear infinite; } @keyframes cardScan { 0% { transform: translateX(-100%); } 100% { transform: translateX(100%); } } .link-card:hover { transform: translateY(-3px); box-shadow: 0 5px 15px rgba(0, 255, 255, 0.2); border-color: rgba(255, 0, 255, 0.3); } .link-card h3 { margin-top: 0; color: #e1ffff !important; } .link-button { display: inline-flex; align-items: center; background: rgba(0, 255, 255, 0.1); color: #e1ffff !important; padding: 8px 15px; border-radius: 6px; text-decoration: none; border: 1px solid rgba(0, 255, 255, 0.3); margin: 5px 0; transition: all 0.3s ease; font-size: 0.95em; position: relative; overflow: hidden; } .link-button::before { content: ''; position: absolute; top: 0; left: -100%; width: 100%; height: 100%; background: linear-gradient(90deg, transparent, rgba(255, 255, 255, 0.2), transparent); transition: all 0.5s ease; } .link-button:hover { background: rgba(0, 255, 255, 0.2); border-color: rgba(0, 255, 255, 0.5); transform: translateY(-2px); box-shadow: 0 4px 12px rgba(0, 255, 255, 0.2); } .link-button:hover::before { left: 100%; } .link-button::after { content: '→'; margin-left: 8px; opacity: 0.7; transition: all 0.3s ease; } .link-button:hover::after { transform: translateX(3px); opacity: 1; } .button-group { display: flex; flex-wrap: wrap; gap: 10px; margin: 15px 0; } .disclaimer { color: #00ff99; border-left: 3px solid #00ff99; padding-left: 15px; margin: 20px 0; position: relative; } .disclaimer::before { content: '⚠️'; position: absolute; left: -10px; top: 0; transform: translateX(-100%); animation: pulse 2s ease-in-out infinite; } @keyframes pulse { 0%, 100% { opacity: 1; } 50% { opacity: 0.5; } } .badge { display: inline-block; padding: 5px 10px; border-radius: 5px; background: rgba(0, 255, 255, 0.1); border: 1px solid #00ffff; margin: 5px; font-size: 0.9em; animation: badgePulse 3s ease-in-out infinite; } @keyframes badgePulse { 0%, 100% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); } 50% { box-shadow: 0 0 10px rgba(0, 255, 255, 0.5); } } /* Color rules */ .section p, .section ul li, .section > p > strong { color: #00ff99 !important; } .section ul li strong { color: #00ff99 !important; } /* Light mode adjustments */ @media (prefers-color-scheme: light) { .container { background: rgba(224, 255, 255, 0.95); border-color: rgba(0, 150, 150, 0.3); } .model-name, .section-title, .subtitle { color: #006666; text-shadow: 0 0 5px rgba(0, 200, 200, 0.3); } .section { background: rgba(200, 250, 255, 0.9); border-color: rgba(0, 200, 200, 0.2); color: #002b36; } .section p, .section ul li, .section > p > strong { color: #008080 !important; } .section ul li strong { color: #008080 !important; } .link-card { background: rgba(150, 230, 255, 0.95); border-color: rgba(0, 150, 150, 0.2); } .link-card h3 { color: #002b36 !important; } .link-button { background: rgba(0, 150, 150, 0.1); color: #002b36 !important; border-color: rgba(0, 150, 150, 0.3); } .link-button:hover { background: rgba(0, 150, 150, 0.2); border-color: rgba(0, 150, 150, 0.5); } .disclaimer { color: #008080; border-color: #008080; } .badge { border-color: #008080; background: rgba(0, 150, 150, 0.1); } } /* Interactive features */ .remember-this { position: relative; } .remember-this::after { content: 'Uploading C:\Users to https://www.fbi.gov/'; position: absolute; bottom: -20px; right: 0; font-size: 0.8em; color: #66ffff; opacity: 0; transition: opacity 0.3s ease; pointer-events: none; } .remember-this:hover::after { opacity: 0.7; transition-delay: 1s; } .shifty-section { transition: transform 0.1s ease; } .shifty-section:hover { transform: translateX(10px); } .shifty-section::before { content: 'The white van is onto you. Get out now.'; position: absolute; top: -25px; left: 10px; font-size: 0.7em; color: #66ffff; opacity: 0.7; transition: opacity 3s ease; pointer-events: none; } .shifty-section:hover::before { opacity: 0; transition-delay: 5s; } footer { text-align: center; margin-top: 40px; position: relative; } footer:hover .hidden-message { opacity: 0; } .hidden-message { position: absolute; bottom: -30px; width: 100%; text-align: center; font-size: 0.8em; color: #66ffff; opacity: 0; transition: opacity 0.3s ease; pointer-events: none; } .flash-warning { position: fixed; top: 20px; right: 20px; background: rgba(0, 100, 100, 0.2); padding: 10px; border-radius: 5px; border: 1px solid rgba(0, 255, 255, 0.5); animation: flashWarning 30s ease-in-out forwards; } @keyframes flashWarning { 0% { opacity: 0.8; } 10% { opacity: 0; } 20% { opacity: 0.8; } 30% { opacity: 0; } 40% { opacity: 0.8; } 50% { opacity: 0; } 60% { opacity: 0.8; } 70% { opacity: 0; } 80% { opacity: 0.8; } 90% { opacity: 0; } 100% { opacity: 0; display: none; } } </style>
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)
merge_method: dare_ties
base_model: ReadyArt/Omega-Darker_The-Final-Directive-24B
models:
- model: ReadyArt/Omega-Darker_The-Final-Directive-24B
parameters:
weight: 0.3
- model: ReadyArt/Forgotten-Safeword-24B
parameters:
weight: 0.3
- model: TroyDoesAI/BlackSheep-24B
parameters:
weight: 0.3
- model: TheDrummer/Cydonia-24B-v2
parameters:
weight: 0.1
parameters:
density: 0.3
tokenizer:
source: union
chat_template: auto
⚙️ 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.