Mistral 7B - The best 7B model to date, Apache 2.0

Mistral 7B is a 7.3B parameter model that:

• Outperforms Llama 2 13B on all benchmarks
• Outperforms Llama 1 34B on many benchmarks
• Approaches CodeLlama 7B performance on code, while remaining good at English tasks

Add a comment

Replies

Best
This is awesome — another open source competitor to OpenAI that can run locally!
I saw a few tweets about this yesterday, great hunt! The quote tweets are hilarious. A few of my favs:
Congratulations! And thank you for the contribution. We are surely going to use it.