Earlier today, AI at Meta released Llama 3!🦙 Marking it as the next step in open AI development! 🚀Llama 3 comes with ~10% improvement compared to Llama 2 and in 2️⃣ sizes, 8B and 70B. 🤯

👉 philschmid.de/sagemaker-llam…

Learn how to run Llama 3 70B at 9ms latency with > 2000…

Meta Llama 3 70B Instruct in Hugging Chat! Go have fun!
huggingface.co/chat/models/me…

huggingface.co/chat/models/me…

LLaMa3 is here! 💥 and AutoTrain already supports it; which means you can fine-tune your LLaMa3 models effortlessly – whether it's locally or on Hugging Face Spaces. Tailor LLaMA 3 to your specific needs by fine tuning it using AutoTrain without writing a single line of code 🚀

Here's all that we know about Meta Llama 3 so far

> Trained on 15T tokens
> 70B and 8B models released (along with instruction tuned)
> 8K context length
> 70B scores 82 on MMLU and 81.7 on Human eval
> 128K vocab tokenizer - utilises 15% less tokens
> Dense model architecture

Llama 3 released! 🚨🔔AI at Meta just released their best open LLM! 👑🚀 Llama 3 is the next iteration of Llama with a ~10% relative improvement to its predecessor! 🤯 Llama 3 comes in 2 different sizes 8B and 70B with a new extended tokenizer and commercially permissive license!…

Big announcement: pleias releases a massive open corpus of 2 million Youtube videos in Creative Commons (CC-By) on Hugging Face. Youtube-Commons features 30 billion words of audio transcriptions in multiple languages, and soon other modalities huggingface.co/datasets/PleIA…

Did you know that Argilla and distilabel datasets have over 6 million hub downloads on the Hub? 🤯

Now, distilabel datasets will be even easier to identify thanks to the new icon added to the Hugging Face Hub—a nice addition to yesterday's release!

github.com/argilla-io/dis…

We've just added a new icon to indicate datasets created using Argilla's Distilabel on the Hugging Face Hub!

Good data is vital for AI so I'm very excited to see the growing number of data tools integrating with the Hub 🚀

💥After months of work, we're thrilled to introduce ⚗️distilabel 1.0.0!

🚀More flexible, robust, and powerful.

🙌 Let's empower the community to build the most impactful datasets for Open Source AI!

Blogpost: argilla.io/blog/introduci…
Github: github.com/argilla-io/dis…

Damn straight! Mistral just dropped the Mistral 8x22B Instruct weights 🔥

> 90.8% on GSM8K maj@8
> 44.6% on math maj@4

Also Mistral throwing shade on Cohere lol

PAG (Perturbed-Attention Guidance) is not getting nearly the attention it deserves, I've adapted it to work on SDXL with diffusers 🧨

...and it DELIVERS! 🤯

Try it here ▶️
huggingface.co/spaces/multimo…

thanks to KU-CVLAB researchers: Donghoon Ahn Hyoungwon Cho et. al ❤️

Demo for IDEFICS-8B is out! (see next tweet for the link ⬇️)
This checkpoint is not optimized to chat, but rather works very well for various tasks, incl visual question answering and document tasks 💬📑
Chatty one is coming soon!

CodeQwen1 1.5 7B - GPU poor ftw! 🔥

> pre-trained on 3 trillion tokens.
> 64K context.
> supports tasks like code generation, code editing, sql, chat and more.
> performs better than deepseek coder and chat gpt 3.5 on SWE bench.
> open access model, weights on the Hub.

📢 Announcing the Hugging Face ML for 3D Course

You'll learn:
🧊 Building blocks of cutting-edge Generative 3D research
🎨 How Gaussian Splatting works
🪄 How to build your own Generative 3D demo

🤑 Free / open-source
📅 Starts May 15, 2024

Sign Up: mailchi.mp/911880bcff7d/m…

Check out our latest blog post to see how our customer Ryght is innovating in the healthcare and life sciences sector with the help of Hugging Face's Expert support program! 🤗

🔗huggingface.co/blog/ryght-cas…

Idefics 2 x Transformers! 🔥

Trying out the Idefics 2 8B in the wild.

Pretty wild that you can do all this in less than 10 lines of code!

Made a quick screencast taking the model out for a spin..

Open source ftw! 🐐

We can do it! 🙌 First open LLM outperforms OpenAI GPT-4 (March) on MT-Bench. WizardLM 2 is a fine-tuned and preferences-trained Mixtral 8x22B! 🤯

TL;DR;
🧮 Mixtral 8x22B based (141B-A40 MoE)
🔓 Apache 2.0 license
🤖 First > 9.00 on MT-Bench with an open LLM
🧬 Used multi-step…

Obsessed with a quote I read that news companies might risk being 'busy dying' if they don't innovate. Don't want that to happen. That's why, after years in newsrooms, I'm thrilled to join @HuggingFace. Can't wait to work on news for AI & AI news! clem 🤗 Brigitte 🤗

Introducing Idefics 2 🤯

An 8B Vision-Language Model - literally punching above its weight.

> Apache 2.0 licensed! 🔥
> Competitive with 30B models like MM1-Chat
> 12 point increase in VQAv2, 30 point increase in TextVQA (compared to Idefics 1)
> 10x fewer parameters than…