Hugging Face

Gradio Sketch in 2 Minutes 🔥

We introduce FAT5 (Flash Attention T5) ⚡ An implementation of T5 in PyTorch with UL2 objective optimized for GPGPU for both training and inference thanks to 13 differents optimizations. The main one is that we have designed a CUDA kernel to expand the Flash Attention by Tri Dao with RPE biases and supports other positional encodings such as RoPE, ALiBi or FIRE. The result kernel is 2 times faster than a SPDA implementation. We also use Triton kernels to optimize certain parts of the architecture, such as the cross-entropy and RMSNorm layer.   The various kernels have been carefully built to be compatible with BF16 and torch.compile to go even faster and achieve efficient pretraining. All other optimizations are described in a 📝 subsequent blog post available on Hugging Face 🤗: https://lnkd.in/eTTUqt7R This methodology enabled us to efficiently pretrain as a proof of concept a FAT5 with 147M parameters in French in a reasonable time (1,461H for 419B tokens), with limited resources (1 A100 i.e. a computational budget of ~ €1,900) and a low carbon footprint (13.5kg eq CO2).   The model's weights are also available on Hugging Face: https://lnkd.in/e-pcAMgN. Not very useful in practice, it's a PoC and not an instructed model (it's planned for later).   All the code is available on GitHub if you want to pretrain your own model in your own language or for a specific domain: https://lnkd.in/eY6e6jHJ ⭐   Ending by indicating that was a joint project with Boris Albar at CATIE 👨💻

KDTalker is wild 🤯 Runs on one 4090 or 3090 🤩 Generates Talking Portraits which are audio-driven - Preserves character identity with fine facial details - Expressions change with the speech, giving high pose diversity - Diffusion based Play with their official gradio website: links in the comments! Coming very soon to the Hugging Face Spaces 🤗

Interior photographers spend HOURS editing lamp lighting. Finegrain just fixed that. Introducing Finegrain Light Switcher App -- an AI tool that instantly transforms off lamps to on in any image. Perfect for: - Real estate listings - Product photography - Interior design portfolios - E-commerce displays Kudos to Denis B. and the rest of the Finegrain team. Try it now on Hugging Face: Find the app link in the comments 💭

This is INSANELY cool 🤯 Chat ui + Orpheus = AI assistant with human-level emotions Type "@josh-tts Hey! [laugh] I'm surprised this works!" ↓ Get speech response that sounds genuinely happy and surprised OR Type "@josh-llm Hey! How is the weather in Amsterdam in July?" ↓ Get speech response from an LLM With this single interface, users can: - Generate human-quality emotional speech - Process images and videos - Create images with Stable Diffusion - Chat with multimodal AI models Orpheus and LLM powered Chat webui is on Hugging Face : https://lnkd.in/gxywSp_d

On March 14, Hugging Face submitted our response to the White House Office of Science and Technology Policy's request for information on the AI Action Plan. In our response (myself, coauthored with Yacine Jernite and Irene Solaiman), the overarching message is the following: Open AI systems and open science are fundamental to creating technology that is more performant, efficiently adopted, and secure. Our recommendations are centered on three interconnected pillars: 1️⃣ Recognize Open Source and Open Science as Fundamental to AI Success: The most advanced AI systems today stand on foundations of open research and software. Research has shown that investment in open systems have a strong economic multiplier effect. We need continued investment in public research infrastructure, compute access, and trusted open datasets. 2️⃣ Prioritize Efficiency and Reliability to Unlock Broad Innovation: Smaller, efficient models enable wider adoption across organizations with varying resources. Purpose-designed AI supports better in-context evaluation and resource utilization. This approach is especially critical in high-risk settings like healthcare. 3️⃣ Secure AI through Open, Traceable, and Transparent Systems: Information security history shows that open, transparent systems are essential for security. Different levels of openness can address various security requirements. Open-weight models that can run in air-gapped environments help manage information risks. Read our blog post (linked in comments) for a more detailed overview and the complete response document!

🪦 🌶️ Data annotation is dead! I just classified and open-sourced a dataset in under 10 minutes. Since the arrival of ChatGPT, many have declared the death of data labeling as we know it. 🛑 But: - Human feedback remains the cornerstone of reliable AI systems. - Pure synthetic data and AI feedback come with many known flaws: lack of diversity, accuracy, and bias amplification. - The alternative proposed by those claiming the end of data annotation is either generating entirely synthetic data or relying on AI-assisted labeling. 🟩 What if we flipped the script? Instead of helping humans with data work, why not have human experts assist AI with data work? Here’s a sneak peek at what we’re building for the open-source community —and an open dataset I created in under 10 minutes assisting Llama-3.3-70B-Instruct powered by Hugging Face Inference Providers. Link to the dataset and pipeline in the first comment.

We just killed 70+ bugs in one update. Gradio's Dataframe is reborn. - Multi-cell selection (finally!) - Column and row freezing, - Searching and Filtering - Full-screen mode - Copy functionality And so much more, to learn about the full release read our Blog on Hugging Face: https://lnkd.in/gA_3SwVP Start using it with `pip install --upgrade gradio` 🔥 For data scientists and Leaderboard enthusiasts, this is the quality-of-life upgrade you've been waiting for. Kudos to Hannah B. Abubakar Abid, and the whole Gradio team! What feature will save you the most time?

Gradio is giving the AI app development power to masses - concept to working app without any code! Gradio-Sketch visual AI application builder has evolved: ✓ Visual component arrangement ✓ Select-and-Add interface building ✓ Event listener configuration ✓ AND NOW AI-POWERED FUNCTION GENERATION (🤩 NEW!) The future of App building isn't coding at all. Gradio Sketch can now generate the whole application code for you. ✅ Simply type `gradio sketch` into your Terminal to open up a WYSIWYG editor that lets you define and modify Gradio components, adjust their layouts, add events and functions, all through a web editor in your browser. 🤠 Or use this hosted version of Gradio Sketch, running on Hugging Face Spaces: https://lnkd.in/gDmTtRjz

Don't sleep on Gemma 3; it's a beast! Here are the results of my latest experiment 👇 Gemma3-27B-it is now available on Hugging Face Inference Providers. So, I decided to use it in my small jailbreak prompt classification benchmark. Here's what I found: 1. I can run the benchmark (100 examples) in under 2 minutes with the Inference API, no need to download anything or use a single GPU. 2. In a few-show setting, it beats all the other models, including leading reasoning models Qwen 32B and DeepSeek R1, and surpasses Llama 3.3 70B with almost 20 points! This is just a small experiment, but I'm thrilled to see the progress of Open Source AI and how Hugging Face enables AI builders to leverage the latest AI advances for their own projects. The results of my experiment are open source, link to the dataset and pipeline in the first comment. Let's go!