werty1248/Llama-3-Ko-8B-OpenOrca

werty1248/Llama-3-Ko-8B-OpenOrca is an 8 billion parameter Llama 3-based causal language model fine-tuned for Korean language tasks. It was trained using LoRA-8bit on the kyujinpy/OpenOrca-KO dataset, building upon the beomi/Llama-3-Open-Ko-8B model. This model demonstrates strong performance on Korean language understanding benchmarks, making it suitable for applications requiring robust Korean natural language processing.