view article Article I fine-tuned a model for free from one prompt, with TRL and the Google Colab CLI sergiopaniego • 11 days ago • 4
view article Article MTEB Leaderboard: From a slow demo to feature-rich leaderboard Samoed • 14 days ago • 22
view article Article How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent nvidia • 22 days ago • 66
Verbatim RAG v1 Collection Hallucination free RAG and out SOTA state-of-the-art extractors • 8 items • Updated 24 days ago • 9
view article Article Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action nvidia • 25 days ago • 83
view article Article Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains JetBrains • 25 days ago • 32
view article Article ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM ibm-research • 30 days ago • 17
📝 Research & Long-Form Blog Posts Collection In-depth technical articles and research pieces published by Hugging Face • 18 items • Updated 29 days ago • 34
view article Article Eight Days in China: What I Learned from the AI Labs, Robotics Startups and Academia matthew-d-white • May 22 • 5
view article Article Harness, Scaffold, and the AI Agent Terms Worth Getting Right sergiopaniego, ariG23498 • May 25 • 122
view article Article Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality ibm-granite • May 14 • 33
MiniCPM-V 4.6 Collection MLX variants of MiniCPM-V 4.6, 1.3B parameters (SigLIP2 400M vision encoder + Qwen3.5-0.8B LLM), repo: https://huggingface.co/openbmb/MiniCPM-V-4.6 • 7 items • Updated May 11 • 1
view article Article EMO: Pretraining mixture of experts for emergent modularity allenai • May 8 • 38