Sao10K/L3-8B-Stheno-v3.2

Sao10K/L3-8B-Stheno-v3.2 is an 8 billion parameter language model developed by Sao10K, fine-tuned from a Llama-3 base. This iteration, Stheno-v3.2-Zeta, is optimized for balanced SFW/NSFW storywriting and narration, alongside improved assistant-style tasks. It features enhanced multi-turn coherency and better adherence to prompts and instructions, making it suitable for diverse conversational and creative generation applications.