view article Article olmo-eval: An evaluation workbench for the model development loop allenai • 3 days ago • 12
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs Paper • 2606.12385 • Published 6 days ago • 3
view article Article How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces mishig • 6 days ago • 21
view article Article Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership clem • 7 days ago • 32
view article Article Designing the hf CLI as an agent-optimized way to work with the Hub celinah, Wauplin • 12 days ago • 56
🌌 Borealis Collection Borealis is a new family of Norwegian-centric instruction-tuned language models from the National Library of Norway. • 24 items • Updated 3 days ago • 10
ClaimExtractor-2605 Collection Extract claims and intents from conversations • 7 items • Updated 1 day ago • 8
CoPE-B Collection Second generation policy-steerable content classification model • 2 items • Updated 20 days ago • 1
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 Text Generation • 335B • Updated 6 days ago • 227k • • 182
Running 7 AI Hardware Choices are Highly Variable and Sparsely Disclosed 📝 7 Explore AI hardware disclosure via interactive visualization