SmolDataEnvs Multi-harness RL Collection Try the three environments, follow the tutorial, and explore the datasets, models and historical RL/SFT results. • 22 items • Updated about 9 hours ago • 3
view article Article The Road to Open Source Hell Is Paved With Good Intentions qgallouedec • 15 days ago • 13
view article Article tokenizers v1: encode, decode and scaling, measured +2 ArthurZ, sbrandeis, mcpotato, lysandre • 17 days ago • 88
view article Article Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL +2 aminediroHF, qgallouedec, kashif, sergiopaniego • 28 days ago • 53
view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • Sep 3 • 147
view article Article Baseten on Hugging Face Inference Providers 🔥 +6 alexker-baseten, rolandcrosby-baseten, squidarth, johan-baseten, celinah, sbrandeis, Wauplin, merve • Aug 6 • 36
view article Article Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident +2 hlarcher, XciD, raphael-gl, chris-rannou • Jul 27 • 507
view article Article Welcome Inkling by Thinking Machines +3 burtenshaw, merve, pcuenq, ariG23498, andito • Jul 15 • 167
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2606.15007 • Published Jun 12 • 20
OpenThinker-Agent2 Collection OpenThinker-Agent2: agentic SFT/RL datasets and 8B/32B models (cold-start SFT, RL, and the OpenThinkerAgent-32B release). • 11 items • Updated Jun 11 • 11
view article Article Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets huggingface • Jun 24 • 56