It's powered by Nous Hermes Llama2 7b. From their docs: "This model stands out for its long responses, lower hallucination rate, and absence of OpenAI censorship mechanisms. [...] The model was trained almost entirely on synthetic GPT-4 outputs. Curating high quality GPT-4 datasets enables incredibly high quality in knowledge, task completion, and style."
I’m a little out of date (busy few weeks), didn’t the Vicuna folks un-housebreak the LLaMA 2 language model (which is world class) with a slightly less father-knows-best Instruct tune?