Двуязычная модель VARCO LLM 13B демонстрирует одни из лучших показателей производительности среди корейских ИИ аналогичного размера. Она обучена на высококачественных наборах данных, что позволяет ей мастерски справляться с генерацией контента и сложными диалогами на корейском и английском языках.
VARCO-LLM is NCSOFT’s large language model, which can be applied to develop various NLP-based AI services such as Q&A, chatbot, summarization, information extraction etc. VARCO-LLM, trained with public pre-training data and internally constructed high-quality Korean data, boasts the highest performance among the Korean LLMs of similar sizes that have been released to date (see https://ncsoft.github.io/ncresearch/ for evaluation results). Our models will continue to be updated and we will also release LLMs that support multiple languages or are fined-tuned to specific tasks. As VARCO-LLM is currently in beta service (29 Aug to 10 Sep 2023), usage fees will not be charged temporally for this period. For inquiries regarding further performance improvement or collaboration for service applications, please contact us via email (varco_llm@ncsoft.com). The VARCO LLM KO/EN-13B-IST is a bilingual instruction-tuned model that is trained with the Korean/English pre-training data and the instruction dataset, both constructed by NCSOFT.