With the growing capability of large language models (LLMs), a new class of models has emerged: Vision Language Models (VLMs). These models can analyze images and videos to describe scenes, create captions, and answer questions about visual content. While running AI models on your own device can be difficult as these models are often computationally demanding, it also offers significant benefits: including improved privacy since your data stays on your machine, and enhanced speed and reliability because you’re not dependent […]

Intel and Hugging Face collaborated to demonstrate the real-world value of upgrading to Google’s latest C4 Virtual Machine (VM) running on Intel® Xeon® 6 processors (codenamed Granite Rapids (GNR)). We specifically wanted to benchmark improvements in the text generation performance of OpenAI GPT OSS Large Language Model(LLM). The results are in, and they are impressive, demonstrating a 1.7x improvement in Total Cost of Ownership(TCO) over the previous-generation Google C3 VM instances. The Google Cloud C4 VM instance further resulted in: […]

Let’s get straight to the point: worldwide, an estimated 220 million people suffer from at least one food allergy, and in the United States alone, this accounts for roughly 10% of the population. This means that if you don’t have an allergy, you’ll likely know someone who does — and it’s not a pleasant situation to be in. This condition affects not only patients’ physical health but also takes a significant toll on their mental well-being and overall quality of […]

We have added Chandra and OlmOCR-2 to this blog, as well as OlmOCR Scores of the models 🫡 TL;DR: The rise of powerful vision-language models has transformed document AI. Each model comes with unique strengths, making it tricky to choose the right one. Open-weight models offer better cost efficiency and privacy. To help you get started with them, we’ve put together this guide. In this guide, you’ll learn: The landscape of current models and their capabilities When to fine-tune models […]

Today, we are announcing that Sentence Transformers is transitioning from Iryna Gurevych’s Ubiquitous Knowledge Processing (UKP) Lab at the TU Darmstadt to Hugging Face. Hugging Face’s Tom Aarsen has already been maintaining the library since late 2023 and will continue to lead the project. At its new home, Sentence Transformers will benefit from Hugging Face’s robust infrastructure, including continuous    

With tools like TRL, TorchForge and verl, the open-source community has shown how to scale AI across complex compute infrastructure. But compute is only one side of the coin. The other side is the developer community; the people and tools that make agentic systems possible. That’s why Meta and Hugging Face are partnering to launch the OpenEnv Hub: a shared and open community hub for agentic environments. Agentic environments define everything an agent needs to perform a task: the tools, […]

We’re thrilled to announce a series of significant advancements across LeRobot, designed to make open-source robot learning more powerful, scalable, and user-friendly than ever before! From revamped datasets to versatile editing tools, new simulation environments, and a groundbreaking plugin system for hardware, LeRobot is continuously evolving to meet the demands of cutting-edge embodied AI. TL;DR LeRobot v0.4.0 delivers a major upgrade for open-source robotics, introducing scalable Datasets v3.0, powerful new VLA models like PI0.5 and GR00T N1.5, and    

TL;DR: After five years of development, huggingface_hub has reached v1.0 – a milestone that marks the library’s maturity as the Python package powering 200,000 dependent libraries and providing core functionality for accessing over 2 million public models, 0.5 million public datasets, and 1 million public Spaces. This release introduces breaking changes designed to support the next decade of open machine learning, driven by a global community of almost 300 contributors and millions of users. 🚀 We highly recommend upgrading to […]

We boosted load_dataset(‘dataset’, streaming=True), streaming datasets without downloading them with one line of code! Start training on multi-TB datasets immediately, without complex setups, downloading, no “disk out of space”, or 429 “stop requesting!” errors.It’s super fast! Outrunning our local SSDs when training on 64xH100 with 256 workers downloading data. We’ve improved streaming to have 100x fewer requests, → 10× faster data resolution → 2x sample/sec, → 0 worker crashes at 256 concurrent workers. Loading data, especially at the terabyte scale, […]

In this blog post, we introduce the idea of a ‘voice consent gate’ to support voice cloning with consent. We provide an example Space and accompanying code to start the ball rolling on the idea.