NousResearch/Yarn-Mistral-7b-128k

NousResearch/Yarn-Mistral-7b-128k is a 7 billion parameter language model developed by NousResearch, extending the Mistral-7B-v0.1 architecture. It is specifically pretrained on long context data using the YaRN extension method, enabling an impressive 128k token context window. This model is optimized for processing and understanding extremely long sequences of text while maintaining strong performance on short-context tasks.