48 repos across 2 sub-areas
Open-source large language models, training frameworks, and natural language processing tools built primarily in Python. The cluster centers on accessible implementations and variants of LLMs—including models like Baichuan, MOSS, and camel—alongside infrastructure for fine-tuning, inference, and dialogue systems. Developers here will find both pretrained models ready for deployment and the underlying frameworks for building and adapting language models to specific tasks.