Mistral AI 7B – beats Llama 2 7B and 13B (mystic.ai)

Their new 7B model beats the Llama 2 7B in all benchmarks that they provided, and in many cases the 13B variation. This is a basic demo for you to try it it, seeing the best results with the instruct variation, and JSON extraction seems good!

Something about the way they launched the model by dropping a magnet link on X with no explanation makes me really like this team