Llama 3.1 Euryale 70B v2.2

A community fine-tuned 70B parameter language model built on Meta's Llama 3.1 base, optimized by Sao10K for creative roleplay, narrative storytelling, and multi-turn conversational immersion. It emphasizes improved system prompt adherence, reasoning, and spatial awareness over general-purpose Llama 3.1 70B deployments. Source: supabase.