They won't give the poor guy a break. This one is especially annoying, because it actually passes couple of tests previous models had issues with.

insane how Prime Intellect grew so fast 🤓

no way we are getting ray replacement in 2025 that's actually sane

Excited to share OpenEnv: frontier-grade RL environments for the open-source community 🔥! huggingface.co/blog/openenv 🧩 Modular interfaces: a clean Gymnasium-style API (reset(), step(), state()) that plugs into any RL framework 🐳 Built for scale: run environments in containers

Indeed it looks like it will be chinese century

🔥 It's here: OpenFold3 is now live. THE open-source foundation model for predicting 3D structures of proteins, nucleic acids & small molecules. This is where the future of drug discovery and biomolecular AI lives. Built by openfold. Hosted on Hugging Face. 👇 more

On-policy distillation is a promising way to train small models, but it’s usually limited to teacher–student pairs sharing the same tokenizer. With our GOLD method, you can now distill across different model families and even outperform GRPO! huggingface.co/spaces/Hugging…

Must read for all model training friends

After ~4 years building SOTA models & datasets, we're sharing everything we learned in ⚡The Smol Training Playbook We cover the full LLM cycle: designing ablations, choosing an architecture, curating data, post-training, and building solid infrastructure. We'll help you

How many visualizations do we want for the blog ?? Thibaud Frere: YES This is so well cooked, i hope Red Dot will give him the deserved award

Guess I have just learnt new stuff about the HF cluster 🤔 thanks Nouamane Tazi

Anybody knows a service, that would scrape all my twitter/scholar info and recommend me papers every week based on that ?