Mawdistical/Feral-Allura-70B
Feral-Allura-70B is a 70 billion parameter finetuned language model developed by Mawdistical, derived from TheSkullery's Unnamed-Exp-70b-v0.7.A. This model is characterized by its explicit content warning, indicating a specialization in generating content that fuses 'bestial wrath' with 'fractured delirium'. It is designed for specific use cases involving mature and unconventional narrative generation, offering a distinct output style compared to general-purpose LLMs.
Loading preview...
Feral-Allura-70B: Explicit Content Finetune
Feral-Allura-70B is a 70 billion parameter language model finetuned by Mawdistical, building upon TheSkullery's Unnamed-Exp-70b-v0.7.A base. This model is explicitly designed for generating explicit content, described as a fusion of 'bestial wrath' and 'fractured delirium'. It caters to niche applications requiring highly unconventional and mature narrative styles.
Key Characteristics
- Explicit Content Focus: Specialized in generating mature and potentially disturbing narratives.
- Unique Thematic Fusion: Combines themes of 'bestial wrath' and 'fractured delirium' for distinct output.
- 70 Billion Parameters: A large model size, suggesting robust generation capabilities within its specialized domain.
- Quantized Formats Available: Provided in GGUF and EXL2 collections for various deployment environments.
Recommended Settings
Optimal performance for this model is achieved with specific generation parameters:
- Temperature: 1.0-1.1
- Min P: 0.02-0.05
- Dynamic Temperature (optional): Multiplier 0.75-0.85, Base 1.8, Length 4.
Use Cases
This model is suitable for developers and creators seeking to generate highly specific, explicit, and unconventional narrative content. Its unique finetuning makes it distinct from general-purpose models, offering a specialized tool for mature and experimental storytelling.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.