Hugging Face

If you're building anything in AI, the best skill you need to be using right now is hugging-face-paper-pages Whatever problem you're facing, someone has probably already published a paper about it. HF's Papers API gives a hybrid semantic search over AI papers. I wrote an internal skill, context-research, that orchestrates the HF Papers API into a research pipeline. It runs five parallel searches with keyword variants, triages by relevance and recency, fetches full paper content as markdown, then reads the actual methodology and results sections. The skill also chains into a deep research API that crawls the broader web to complement the academic findings. The gap between "a paper was published" and "a practitioner applies the insight" is shrinking, and I think this is a practical way to provide relevant context to coding agents. So you should write a skill on top of the HF Paper skill that teaches the model how to think about research, not just what to search for.

Protected Spaces with Public URLs now available on Hugging Face You can now set your Spaces to protected, making them private on Hugging Face while still keeping their URL publicly accessible This is useful for deploying production-ready demos or internal tools without exposing model weights, prompts, or proprietary logic Combined with custom domains you can also host your website on Hugging Face changelog: huggingface.co/changelog/prot…

High quality STEP dataset from Shanghai QI ZHI institute. 23.9 TB in size huggingface.co/datasets/OpenS…

Map-Anything v1 (Universal Feed-Forward Metric 3D Reconstruction) demo is now available on Hugging Face Spaces. Built with @Gradio and integrated with @rerundotio , it performs multi-image and video-based 3D reconstruction, depth, normal map, and interactive measurements.

Don't panic. GLM-5.1 will be open source.

Yep, Composer 2 started from an open-source base! We will do full pretraining in the future. Only ~1/4 of the compute spent on the final model came from the base, the rest is from our training. This is why evals are very different. And yes, we are following the license through our inference partner terms.

Looks like it’s confirmed Cursor’s new model is based on Kimi! It reinforces a couple of things: - open-source keeps being the greatest competition enabler - another validation for chinese open-source that is now the biggest force shaping the global AI stack - the frontier is no longer just about who trains from scratch, but who adapts, fine-tunes, and productizes fastest (seeing the same thing with OpenClaw for example).

cancel your weekend and come fix open source! you can train, build, eval a solution to deal with ai slop in open source repos. icymi, most major os repos are drowning in ai generated prs and issues. it's coming from multiple angles: - well intentioned contributors scaling too fast - students trying out ai tools and not knowing best practices - rampant bots trying to get anything merged we need a solution that allows already resource constrained maintainers to carry on doing their work, without limiting genuine contributors and/or real advancements in ai coding. let's build something that scales and enables folk to contribute more. we don't want to pull up the drawbridge. I made this dataset and pipeline from all the issues and PRs on transformers. It's updated hourly so you can get the latest versions.

Excited to release: AgentUI > a fresh chat interface - natively multi-agent > agents coordinate via reports and figures > plug+play any open/closed model as sub-agent > agents specialise in code, web search, multimodal... Try it here: huggingface.co/spaces/lvwerra…

this guy has 29 models on huggingface at page 2 ranking. no lab behind him. no sponsorship. $2,000 from his own pocket on GPU rentals. he compressed GLM-4.7 to run on a MacBook and quantized Nemotron Super the week it dropped. all public. all free. nvidia is a trillion dollar company with hundreds of teams but they are not the ones quantizing models middle of the night and pushing them out before sunrise. if nvidia stopped tomorrow their employees stop working. people like @0xSero would not. that is the difference between a paycheck and a mission. @NVIDIAAI you talk about making AI accessible. the people actually doing it are right here. 29 models deep burning their own compute with no ask except more hardware to keep going. you do not need to build another program. just look at who is already building for you. one GPU to this man would produce more public value than a hundred internal sprints. i am not asking for charity. i am asking you to invest in someone who already proved it.

Talked with @dee_bosa @CNBC about @nvidia and everything open-source AI! Some key points: - Nvidia is the new American open-source AI king - 30% of fortune 500 are using Hugging Face and our goal is to get to the majority of them by the end of the year - Agents will be much more open-source based than chatbots (ex OpenClaw) - Agents empower all to train, fine-tune, and run their own models based on open-source - We crossed 15M AI builders on HF and hope to have as much agents using the platform by the end of the year. Agents are the new users and customers of tech platforms

Not enough people are talking about NVIDIA's new Nemotron-3-Nano (4B) model! 🤯 Hybrid Mamba + Attention architecture, designed as a unified model for reasoning and non-reasoning tasks. So small and efficient, it can run 100% locally in your web browser at 75 tokens per second.

OpenMed is the #1 most referenced organization powering open-source AI research on Hugging Face. This is the official State of Open Source report, Spring 2026. I started this 8 months ago.

it's raining 3D/world models I was going to take time off but just cancelled to catch up! 🥲

Talked about it with @dee_bosa @CNBC here!

Nvidia just crossed Google as the biggest org on @huggingface with 3,881 team members on the hub. I'm officially calling it: Nvidia is the new American king of open-source AI!

Introducing the Daily Papers SKILL.md Enables agents to > read paper content as markdown > search papers > find linked @huggingface models and datasets > fetch the papers API > and more! Link below ⬇️

Is olmOCR-bench getting close to saturation? Top score is now 85.9%. Yesterday @datalabto took #1 with chandra-ocr-2. A year ago, the best was 79. Visualised the race to get there using @huggingface leaderboard data

NEW SOTA OCR MODEL DROPPED Congrats to @VikParuchuri and team for releasing Chandra OCR 2! - 85.9% on olmocr bench, making it first place 🏆 - 90+ language support - 4B model - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support Compare every OCR model on the hub and choose the one adapted to your needs 👇

🔥 Meet Mistral Small 4: One model to do it all. ⚡ 128 experts, 119B total parameters, 256k context window ⚡ Configurable Reasoning ⚡ Apache 2.0 ⚡ 40% faster, 3x more throughput Our first model to unify the capabilities of our flagship models into a single, versatile model.