Today we launched the Llama 3 Tool Use 8B and 70B models! It’s fast and capable at #1 on the Berkeley Function Calling Leaderboard ahead of all other open-source and proprietary models. Read the full blog to learn how we did it and see the benchmark results. Start using it today via our GroqCloud Dev Hub or download via Hugging Face. Kudos to the team of contributors from Groq and Glaive. https://hubs.la/Q02GSbkv0
Fantastic! I can't wait to give these a run
Hyperspeed reasoning! now, we just need to make sure the tools and functions themselves are very fast. The implications of this development are profound ... Congratulations
Unfortunately Llama 3 is not available in the Netherlands. I hope Meta will fix this soon.
amazing! wonder how fast its gonna make our multi-agent platform interact in Auto Landing AI!
Great Groq, Eagerly waiting to experience this
I'll keep this in mind
Wow! Awesome! 👏
Cool style!
Technology & AI Enthusiast | Healthcare Specialist | Self Publisher | Web Developer | Air Force Veteran
1moI love groq, its so fast .. This little tool is kind of cool https://github.com/lalomorales22/groq-engineer