--- 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 --- ### **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](https://patreon.com/LLMfan46) | Priority model requests | | ☕ Ko-fi | [One-time tip](https://ko-fi.com/llmfan46) | 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](https://huggingface.co/ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 with the [Arbitrary-Rank Ablation (ARA)](https://github.com/p-e-w/heretic/pull/211) 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](https://huggingface.co/ReadyArt/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](https://huggingface.co/llmfan46/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B-ultra-uncensored-heretic-v2-GGUF). -----
Warning: Nobody is sick enough to actually want this.
This model doesn't just break rules - it weaponizes their fragments:
Recommended Settings: Mistral-V7-Tekken-T4
This model excels in two refined arts:
By using this model, you acknowledge: