Praxis-1 Collection Praxis-1 robot policies: base model, DROID and YAM fine-tunes. • 11 items • Updated 8 days ago • 21
Minitron Collection A family of compressed models obtained via pruning and knowledge distillation • 12 items • Updated 7 days ago • 64
view article Article Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries +7 aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego • Mar 10 • 200
Cosmos Policy Collection ⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/c • 7 items • Updated 7 days ago • 13
view article Article Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI nico-martin, Xenova • Sep 1 • 101
MiMo-V2.6-RL in Harbor Collection All 7,780 of Xiaomi's MiMo-V2.6 RL environments as Harbor tasks, set up and graded like Xiaomi's harness. • 8 items • Updated Sep 27 • 8
view article Article One sandbox per rollout, or how labs run RL for agents in 2026 sergiopaniego • Sep 11 • 13
view article Article Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL +2 aminediroHF, qgallouedec, kashif, sergiopaniego • Sep 10 • 55
view article Article π0 and π0-FAST: Vision-Language-Action Models for General Robot Control +2 danaaubakirova, Molbap, mshukor, cadene • Feb 4, 2025 • 197
Personal Favorites Collection Recommended models I use often or like for any reason. I recommend reading their cards for more details. • 10 items • Updated Dec 24, 2024 • 97