🤯🤯 You can now create a chatbot on ANY GitHub repo using the Llama 3.1 405B model with Hugging Face assistants -- FOR FREE! 💰 This is insane! 🚀 Link: clem 🤗 Julien Chaumond

Follow @satvikps more updates on AI!

@huggingface @ClementDelangue @julien_c Built-in tool calling with Brave Search (web search) and Wolfram Alpha (math calcs)

@huggingface @ClementDelangue @julien_c This is interesting! But how we activate these tools?

Their RAG pipeline probably needs some work since in its current form it's prone to heavy hallucination. I have no nor do I use `click` in the repo. This is Llama 3.1 70B Instruct (405B was overloaded, but they use an FP8 which may or may not make it better than 70B 3.1 at FP16).

@huggingface @ClementDelangue @julien_c Very cool. Kudos @ClementDelangue & @huggingface 🙌 Thx @satvikps for making us aware of this use-case 🙏🏽

@valb00 @huggingface @ClementDelangue @julien_c Thank you :)

@huggingface @ClementDelangue @julien_c Absolutely incredible! 🎉 The ability to create chatbots on any GitHub repo with Llama 3.1 for free is a game changer! Major kudos to @huggingface for making this accessible to everyone. Can't wait to see what innovative solutions come out of this! 🚀👏

@huggingface @ClementDelangue @julien_c What's the cost of running this?

@huggingface @ClementDelangue @julien_c Also check out @mutableai

@huggingface @ClementDelangue @julien_c Did some test and seems not to recursively indexing the repo/pages. Would also be to heavy anyways. So its not too useful then...