Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🤯🤯 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

Satvik Paramkusham

1,150 subscribers

162,848 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Satvik Paramkusham1 year ago

Follow @satvikps more updates on AI!

Petamber1 year ago

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

Satvik Paramkusham1 year ago

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

Rick Lamers1 year ago

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).

🔯 Balanced Acceleration (b/acc) ☮️1 year ago

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

Satvik Paramkusham1 year ago

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

willk241 year ago

@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! 🚀👏

Ajay || Building Flozi1 year ago

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

Omar Shams1 year ago

@huggingface @ClementDelangue @julien_c Also check out @mutableai

Thomas Seidel1 year ago

@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...

Related Videos

You can now try Llama 3.1 405B for free (link below)! This is the largest open-source model out there, and for the first time, an open model is competitive with closed models. This time around, Meta did something new: Llama 3.1 has a license that allows developers to use it to enhance other models. For the first time, you can distill Llama 3.1 405B's capabilities into a smaller, more practical model for your use case. First, here is the link where you can play with Llama 3.1 for free: The model is hosted in Tune Studio, an end-to-end platform for developing applications using Large Language Models. They are sponsoring this post. Take a look at the attached video. It will show you how you can fine-tune a simple model using Llama 3.1 without leaving the platform: 1. You can create an empty dataset 2. Use the playground to generate and record interactions with Llama 3.1 3. Modify the dataset directly using the playground 4. Export the data and fine-tune a smaller model Fast and easy! As long as you have a web browser, you can start experimenting with fine-tuning and Llama 3.1. That's all it takes!

You can now try Llama 3.1 405B for free (link below)! This is the largest open-source model out there, and for the first time, an open model is competitive with closed models. This time around, Meta did something new: Llama 3.1 has a license that allows developers to use it to enhance other models. For the first time, you can distill Llama 3.1 405B's capabilities into a smaller, more practical model for your use case. First, here is the link where you can play with Llama 3.1 for free: The model is hosted in Tune Studio, an end-to-end platform for developing applications using Large Language Models. They are sponsoring this post. Take a look at the attached video. It will show you how you can fine-tune a simple model using Llama 3.1 without leaving the platform: 1. You can create an empty dataset 2. Use the playground to generate and record interactions with Llama 3.1 3. Modify the dataset directly using the playground 4. Export the data and fine-tune a smaller model Fast and easy! As long as you have a web browser, you can start experimenting with fine-tuning and Llama 3.1. That's all it takes!

Santiago

55,609 views • 1 year ago

This is SO good. You can now find the model you need among 1.6M models at Hugging Face! 🤗 link to free app in 🧵↓

This is SO good. You can now find the model you need among 1.6M models at Hugging Face! 🤗 link to free app in 🧵↓

Charly Wargnier

26,614 views • 1 year ago

With the release of Llama 3.1 405B, @TogetherCompute built LlamaCoder — an open source web app that can generate an entire app from a prompt. The repo has now been cloned by hundreds of devs on GitHub and starred 2K+ times. More on this project ➡️

With the release of Llama 3.1 405B, @TogetherCompute built LlamaCoder — an open source web app that can generate an entire app from a prompt. The repo has now been cloned by hundreds of devs on GitHub and starred 2K+ times. More on this project ➡️

AI at Meta

260,560 views • 1 year ago

Our Llama-3.1-Nemotron-70B-Instruct model is a leading model on the 🏆 Arena Hard benchmark (85) from Arena. Arena Hard uses a data pipeline to build high-quality benchmarks from live data in Chatbot Arena, and is known for its predictive ability of Chatbot Arena Elo score as well as separability between helpful and less helpful models. Use our customized model Llama-3.1-Nemotron-70B to improve the helpfulness of LLM generated responses in your applications. 📥 Try on our API catalog: 📥 On GitHub: 📥 Or on Hugging Face:

Our Llama-3.1-Nemotron-70B-Instruct model is a leading model on the 🏆 Arena Hard benchmark (85) from Arena. Arena Hard uses a data pipeline to build high-quality benchmarks from live data in Chatbot Arena, and is known for its predictive ability of Chatbot Arena Elo score as well as separability between helpful and less helpful models. Use our customized model Llama-3.1-Nemotron-70B to improve the helpfulness of LLM generated responses in your applications. 📥 Try on our API catalog: 📥 On GitHub: 📥 Or on Hugging Face:

NVIDIA AI Developer

140,756 views • 1 year ago

So ace. Google just released Gemini Code Wiki. A free too that generates interactive docs from any GitHub URL 🤯 The tool lets you: → Chat with Gemini to understand *any* repo → Visualize code structure → Create docs from public repos 100% free. Link in 🧵↓

So ace. Google just released Gemini Code Wiki. A free too that generates interactive docs from any GitHub URL 🤯 The tool lets you: → Chat with Gemini to understand any repo → Visualize code structure → Create docs from public repos 100% free. Link in 🧵↓

Charly Wargnier

66,859 views • 6 months ago

Llama 3.1 Now Available in VSCode as a Code Assistant via Groq Inc 🚨 You can now use this new AI at Meta model directly in VSCode using the CodeGPT extension My first impression: The model is incredible 🚀

Llama 3.1 Now Available in VSCode as a Code Assistant via Groq Inc 🚨 You can now use this new AI at Meta model directly in VSCode using the CodeGPT extension My first impression: The model is incredible 🚀

Daniel San

263,015 views • 2 years ago

🚨UNCANNY VALLEY: SO, TURNS OUT AI WON’T REPLACE HUMANS AFTER ALL? While others focus on AI replacing humans, Hugging Face is proving the opposite: community drives progress. With new models, datasets, and apps added every ten seconds, the platform grows faster than any one company could manage alone. clem 🤗: "You can replicate technology. You can’t replicate momentum." Uncanny Valley with Hugging Face CEO clem 🤗 — only on

🚨UNCANNY VALLEY: SO, TURNS OUT AI WON’T REPLACE HUMANS AFTER ALL? While others focus on AI replacing humans, Hugging Face is proving the opposite: community drives progress. With new models, datasets, and apps added every ten seconds, the platform grows faster than any one company could manage alone. clem 🤗: "You can replicate technology. You can’t replicate momentum." Uncanny Valley with Hugging Face CEO clem 🤗 — only on

Mario Nawfal

157,869 views • 1 year ago

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

Santiago

97,505 views • 1 year ago

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

Paul Couvert

148,975 views • 5 months ago

Jack Dorsey’s company just released a free AI agent called Goose 🤯 It’s a local coding agent with 35,000+ GitHub stars that works with almost any AI model. Think of it like a free alternative to Claude Code that you can install, run forever, and customize however you want. This might be one of the best free AI coding tools available right now. 🚀

Jack Dorsey’s company just released a free AI agent called Goose 🤯 It’s a local coding agent with 35,000+ GitHub stars that works with almost any AI model. Think of it like a free alternative to Claude Code that you can install, run forever, and customize however you want. This might be one of the best free AI coding tools available right now. 🚀

Julian Goldie SEO

33,246 views • 3 months ago

Awesome to see the collab between Kaggle and Hugging Face. Now you can use any model from Hugging Face directly in Kaggle. Previously, we had to download and upload the models as datasets. This was much needed 🚀

Awesome to see the collab between Kaggle and Hugging Face. Now you can use any model from Hugging Face directly in Kaggle. Previously, we had to download and upload the models as datasets. This was much needed 🚀

abhishek

25,639 views • 1 year ago

🤯 This is absolutely insane. You can clone any voice locally on your computer using only 3 seconds of reference audio! Entirely open-source.

🤯 This is absolutely insane. You can clone any voice locally on your computer using only 3 seconds of reference audio! Entirely open-source.

Marcel Pociot 🧪

459,873 views • 2 years ago

#ChatGPT for GitHub! 🤯 With the new #AskTheCode plugin, you can crawl and analyze GitHub repos and answer any questions you have about your codebase! 🔥 Whether you're starting a new project or working on an old favorite, this ChatGPT plugin's got you covered! Link below ↓

#ChatGPT for GitHub! 🤯 With the new #AskTheCode plugin, you can crawl and analyze GitHub repos and answer any questions you have about your codebase! 🔥 Whether you're starting a new project or working on an old favorite, this ChatGPT plugin's got you covered! Link below ↓

Charly Wargnier

113,956 views • 2 years ago

This guy literally built an ENTIRE operating system with Claude Code 🤯 now he is showing you exactly how. he dropped a 2+ hour masterclass *AND* a guide on the frameworks and included a free GitHub repo to get you coding right away. you seriously need to check this out 👇

This guy literally built an ENTIRE operating system with Claude Code 🤯 now he is showing you exactly how. he dropped a 2+ hour masterclass AND a guide on the frameworks and included a free GitHub repo to get you coding right away. you seriously need to check this out 👇

Charly Wargnier

167,939 views • 2 months ago

That's what a French engineer (Julien Allali) is building for fun (spotted by Remi Fabre) 🤯🤯🤯 Things like that are making me excited about the power of open-source and collaboration for robotics that Pollen Robotics & Hugging Face can unleash! Let's build the future! 🦾🦾🦾

That's what a French engineer (Julien Allali) is building for fun (spotted by Remi Fabre) 🤯🤯🤯 Things like that are making me excited about the power of open-source and collaboration for robotics that Pollen Robotics & Hugging Face can unleash! Let's build the future! 🦾🦾🦾

clem 🤗

52,851 views • 11 months ago

It’s INSANE how easy it is to Create Photorealistic Characters and Animate them within Minutes using Unreal Engine. Ideation to Render now takes a few hours ONLY and that’s super liberating for artists who want to tell stories 🤯 With Unreal you can now create facial animations for your Metahuman just by using audio without any complex setups, or you can even use your Iphone and Webcam to drive the face animations. It uses AI to predict facial muscle movements, and the results are honestly insane. This is a total game-changer, especially for filmmakers, storytellers and even game developers.

It’s INSANE how easy it is to Create Photorealistic Characters and Animate them within Minutes using Unreal Engine. Ideation to Render now takes a few hours ONLY and that’s super liberating for artists who want to tell stories 🤯 With Unreal you can now create facial animations for your Metahuman just by using audio without any complex setups, or you can even use your Iphone and Webcam to drive the face animations. It uses AI to predict facial muscle movements, and the results are honestly insane. This is a total game-changer, especially for filmmakers, storytellers and even game developers.

Bad Decisions Studio

15,201 views • 10 months ago

🤯🤯🤯 THE CURVE IS NO MORE 🤯🤯🤯 Pixelcraft Studios and #AavegotchiDAO are now funded with 30M DAI and ready to SHIP 🚢 A new chapter begins today for $GHST and #GOTCHIGANG ARE YOU READYYY?!?! 🚀🚀🚀🚀🚀

🤯🤯🤯 THE CURVE IS NO MORE 🤯🤯🤯 Pixelcraft Studios and #AavegotchiDAO are now funded with 30M DAI and ready to SHIP 🚢 A new chapter begins today for $GHST and #GOTCHIGANG ARE YOU READYYY?!?! 🚀🚀🚀🚀🚀

Aavegotchi

152,725 views • 3 years ago