AI summary: The Nous-Hermes-Llama2-13b, a state-of-the-art language model, has been fine-tuned on over 300,000 instructions for improved performance. The model, developed by Nous Research in collaboration with Teknium, Emozilla, Huemin Art, and Redmond AI, offers longer responses, lower hallucination rates, and lacks OpenAI censorship mechanisms. It has achieved top benchmarks in several categories, including ARC-c, ARC-e, Hellaswag, and OpenBookQA. The model is available for download on Hugging Face and can be used for a wide range of language tasks.
Read more…

%d bloggers like this: