We just OCR'd 27,000 arxiv papers into Markdown using an open 5B model, 16 parallel HF Jobs on L40S GPUs, and a mounted bucket. Total cost: $850 Total time: ~29 hours Jobs that crashed: 0 This now powers "Chat with your paper" on http://
hf.co/papers
@clementdelangue
-
Open source OCR processes 27000 arxiv papers efficiently
By
–
-
Coding with Robots: ElevenLabs and Reachy Mini Collaboration
By
–
favorite AGI/sci-fi vibe these days is coding a robot code together with the robot
— Thomas Wolf (@Thom_Wolf) 10 avril 2026
here vibe-pluging @ElevenLabs in @reachymini for a talk later today pic.twitter.com/0m65ozY8JAfavorite AGI/sci-fi vibe these days is coding a robot code together with the robot here vibe-pluging @ElevenLabs in @reachymini for a talk later today
→ View original post on X — @clementdelangue, 2026-04-10 18:22 UTC
-
Hugging Face Kernels: Enabling AI Builders with Optimized Binary Operations
By
–
In a world where writing code to build websites and apps is trivial (thank you Lovable, Cursor, Claude,…), the real differentiation for you and your company (and what makes you successful) will be how you manage to train, run and optimize AI models yourself. That's why at Hugging Face, we're doubling down on enabling more to become AI builders rather than AI users. We're releasing this week Kernels on the Hugging Face hub. This repo type is for the hardcore AI engineers among you. Kernels are collections of optimized binary operations where hardware providers support is a first-class citizen: – CUDA – ROCm – Apple Silicon – Intel XPU Expect to see more of this repo type on Hugging Face in the coming days. Featured here: the Flash Attention kernel from @sgl_project team ❤️
→ View original post on X — @clementdelangue, 2026-04-10 15:23 UTC
-
NS Orthogonalization Dominates MuonAdamW Optimizer Baseline Research
By
–
Ran autoresearch on hf to see whether anything can beat MuonAdamW baseline Biggest takeaway: NS orthogonalization is a very strong attractor that absorbs most gradient modifications you throw at it. See all the artifacts at huggingface.co/datasets/mish…
→ View original post on X — @clementdelangue, 2026-04-10 13:23 UTC
-
Hermes Agent Traces on Hugging Face Platform
By
–
hermes agent traces on Hf would be pretty neat attn: @Teknium @NousResearch @ClementDelangue huggingface.co/changelog/age…
→ View original post on X — @clementdelangue, 2026-04-10 02:20 UTC
-
Transformers.js Reaches 4.4M Monthly Downloads in March 2026
By
–
Transformers.js monthly downloads 🤯📈
— Xenova (@xenovacom) 9 avril 2026
2023/03 ▏3.2K
2024/03 █ 266K
2025/03 ██ 764K
2026/03 ████████████ 4.4M
Thanks so much to this amazing community! 🤗 We're excited to see what you build next! pic.twitter.com/ruvsLMQNGlTransformers.js monthly downloads 🤯📈 2023/03 ▏3.2K 2024/03 █ 266K 2025/03 ██ 764K 2026/03 ████████████ 4.4M Thanks so much to this amazing community! 🤗 We're excited to see what you build next!
→ View original post on X — @clementdelangue, 2026-04-09 16:21 UTC
-
Open Weight Model Ranks First in Cybersecurity Benchmarks
By
–
Do you understand what this means? For the first time, an Open Weight models is #1 on CyberSecutity. Sure there’s Mythos but we don’t have it :p Don’t let them trick you
-
Silicon Valley quietly adopts Chinese open source AI models
By
–
Silicon Valley is quietly running on Chinese open source AI models. Here are the receipts: → Cursor confirmed last month that Composer 2 is built on Moonshot's Kimi K2.5 → Cognition's SWE-1.6 model is likely post-trained on Zhipu's GLM → Shopify saved $5M a year by switching to Alibaba’s Qwen model. Airbnb CEO Brian Chesky has also said: "We rely a lot on Qwen. It's very good, fast, and cheap." And now Zhipu dropped GLM-5.1, an open source model that performs almost as well as Opus on coding benchmarks. 📌 More on the Anthropic + OpenClaw drama and what I'm learning about AI on the ground in China in my new post: creatoreconomy.so/p/the-all-… Peter Yang (@petergyang) As much as I love using Claude Max and ChatGPT Pro, I don't think these all-you-can-use AI subscriptions will last forever. Here's my new deep dive that covers: → Why Anthropic cut off OpenClaw access → How to run local models on your Mac → What I'm seeing on the ground in China 📌 Read now: creatoreconomy.so/p/the-all-… — https://nitter.net/petergyang/status/2041989206495653915#m
→ View original post on X — @clementdelangue, 2026-04-09 14:30 UTC
-
Pi Agent Publishes Excel Traces to HuggingFace
By
–
Someone used Pi to build an Excel agent… then published all the traces from it to HuggingFace🤯 Just point your agent at this changelog and tell it to publish its traces to HuggingFace! huggingface.co/changelog/age…
→ View original post on X — @clementdelangue, 2026-04-09 14:19 UTC
-
Open-Source Security Risks and Maintenance Funding Solutions
By
–
Feels like one of the cybersecurity risks over the coming months will be widely used open-source projects that are simply too lightly maintained for how critical they’ve become. A few ways to help: – fund open source more, and reward maintainers better – bring some of the most critical projects under more resourced umbrellas like @linuxfoundation or @huggingface Which projects would actually make sense to join HF if we wanted to help them on cybersecurity?
→ View original post on X — @clementdelangue, 2026-04-09 13:46 UTC