I’ve been leading a secret project for months … and the word is finally out!
🛠️ I'm proud to announce the Llama 3 Groq Tool Use 8B and 70B models 🔥
An open source Tool Use full finetune of Llama 3 that reaches the #1 position on BFCL beating *all* other models, including proprietary ones like Claude Sonnet 3.5, GPT-4 Turbo, GPT-4o and Gemini 1.5 Pro.
This has been months of hard work from me, my great colleagues at Groq and our awesome collaborators over at @glaive.ai (h/t Nishant Aklecha Sahil Chaudhary).
The model has been trained on synthetic data _only_. This is a powerful full finetune, not a LoRA. Yes, we've checked rigorously for overfitting using the LMSYS described robust decontamination techniques, they only score 5.6% on SFT synthetic data and 1.3% on synthetic DPO data.
Now available on the Groq API for blazing fast speeds of 1050 tok/s for 8B and 330 tok/s for the 70B model or download the open source weights from Hugging Face to start exploring & tinkering.
Check out the full blog post for more details, find all links in the reply below.
Chairman at U First Capital
1wTo your second point, the dialog is where the inference speed shines. I have been playing with Groq and am amazed by its speed across a variety of genres of queries! Kudos Sunny and team!!!