NCSOFT/Llama-VARCO-8B-Instruct

NCSOFT/Llama-VARCO-8B-Instruct is an 8 billion parameter generative language model developed by NC Research, Language Model Team. Built upon Meta-Llama-3.1-8B, it is continually pre-trained with Korean and English datasets and fine-tuned using SFT and DPO in Korean. This model is specifically optimized for high proficiency in Korean language understanding and generation, while maintaining strong English capabilities. It is best suited for applications requiring robust bilingual performance, particularly in Korean contexts.