Hugging Face

Harness adapters training is now live! We are training LoRA adapters on LFM2.5 / LFM3 from @liquidai and the recent Twil-9B model from @thewebAI using RL to make them more efficient and accurate on agentic tasks! You can follow the training going live here: harness-hub-harness-adapters… huggingface.co/blog/harness-…

YOUR data deserves YOUR own, private model. Now, let @HuggingFace's ML Intern build it for you. Connect your data, files, mcps. And call it from Slack.

Introducing RoboColosseum An open robot eval initiative by @huggingface @BitRobotNetwork @eaic_sg @DJiafei Access: - 100+ robots (@UnitreeRobotics G1s, @LeRobotHF SO-101s, YAMs, Franka and more) - 140+ in-the-wild scenes - Open rollout data - 10,000 FREE eval hrs Thread ↓

Something’s cooking in the lab 🧪🤗 NeurIPS 2026 × ML Intern Reproduction hackathon. Coming soon. We are very excited!!

OpenResearch now has @TrackioApp built in 📈 Your agent logs its experiments to Trackio, charts open right next to each run, and it reads the curves back to decide what to try next. Open source and local-first. Running on HF Jobs, Modal, k8s or Slurm? Save a @huggingface Space and every run lands there, private Spaces included. Check it out: github.com/alphaXiv/OpenRese…

The AI question in financial services has moved from which model to use to where that model is allowed to run. New post with @TangriKunal and @huggingface on why firms want to run models on their own infrastructure, and how governance gets them approved to run there. Read it here: farsight-ai.com/news/open-mo…

We teamed up with @huggingface to give away $20,000 to anyone who's building with Beam 🤗 Use Beam for any project - make a demo or a dataset, benchmark the model, create an RL environment - and comment your link in the model's repo page by Monday, November 2. We choose the winners. Winners choose cash or credits. Claim $25 in Hugging Face credits to build with Beam and enter the competition 👇 huggingface.co/reflection/Be…

Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners. We're releasing: - Weights, tokenizer, and reference implementation - BF16, FP8 and NVFP4 weights and a DFlash2 drafter - The open source harness we built and trained Beam on: Mirror CLI Weights and model card on Hugging Face: huggingface.co/reflection

🚨 The incentives to share scientific knowledge openly are crumbling. Historically, researchers shared scientific knowledge for two primary reasons: (1) the prestige conferred by discovery, and (2) a sense of expanding the pool of human knowledge. Even within industry, scientific discovery was far too vast an endeavor for a single scientist or team to tackle alone. So scientists explored different frontiers, usually published their findings, and collectively moved the field forward. However, as more scientific knowledge is uncovered simply by throwing massive compute at autonomous agents with minimal human intervention, these incentives are breaking down: (1) discoveries are becoming commoditized. If anyone could have found the same result simply by running the same agentic prompt with enough compute, the prestige of discovery and the pride in one's work disappears, a shift we are already witnessing in software engineering. (2) the explosion of low-quality, low-barrier publications makes genuine breakthroughs increasingly difficult to filter, discover, and appropriately credit. (3) and for companies, keeping discoveries proprietary is increasingly advantageous. Instead of publishing and waiting for the broader scientific community to build upon the work, an organization can simply turn its own compute back onto the problem to iterate faster internally. In the short term, the incentives reward secrecy. But my goal -- and at Hugging Face, our goal -- is the sustainable, long-term expansion of human knowledge that survives individual, closed companies. So we have to build new tools that reward and facilitate open sharing of knowledge. If agents are accelerating discovery, we are going to figure out how to use agents and other tools to preserve scientific integrity. Starting with this: Paper Reproductions with ML Intern -- we’ve made it possible to take a published paper and task agents with independently reproducing its experiments, helping create more signals (e.g. open artifacts) that can help identify high-quality work.

5 years ago, we released @Gradio to make it easier to build frontends for AI apps. At that time, that was the main blocker for making AI more accessible to the community. But this is no longer a challenge. So we asked ourselves and other developers: "what are the main challenges that you face now when building and using AI apps" – and we are now working hard to redesign Gradio from scratch to solve these issues!