darkcloudai/huskylm-2.5-8b

The darkcloudai/huskylm-2.5-8b is an 8 billion parameter causal language model developed by Darkcloud AI, built upon Meta's Llama 3 architecture with an 8192 token context window. It is fine-tuned using a combination of Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and proprietary Reinforcement Learning from Artificial Intelligence Feedback (RLAIF) methodologies. This general-purpose chat model excels in strong system prompt adherence, state-of-the-art coding abilities across multiple languages, exceptional conversational skills, and best-in-class multilingual support, making it suitable for diverse applications from writing assistance to in-game NPC interactions.