ArticleHugging Face Blog@hugging-face-blog · Jun 12 · 8 minolmo-eval: An evaluation workbench for the model development loop00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 11 · 18 minProfiling in PyTorch (Part 2): From nn.Linear to a Fused MLP00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 9 · 13 minCan Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 9 · 13 minIntroducing North Mini Code: Cohere’s First Model For Developers00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 9 · 5 minHow an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 9 · 5 minNeuroBait: I fine-tuned a model to spark dopamine for ADHD brain00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 9 · 9 minMigrating Your GitHub CI to Hugging Face Jobs00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 8 · 7 minThe crash that vanished: control and emergence in a five-model economy00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 8 · 5 minThe Open Source Community is backing OpenEnv for Agentic RL00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 7 · 3 minAmazing Digital Dentures (a failed project)00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 7 · 2 minSponsors especially OPENAI CODEX voucher usage for codex - openAI challange00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 7 · 4 minHer · हेर — a detective for your Claude Code sessions00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 6 · 6 minFive labs, five minds: building a multi-model finance drama on small models00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 6 · 4 minPersona Atlas: Mapping How Famous Minds Think00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 5 · 6 minThousand Token Wood: shipping a multi-agent economy on a 3B model00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 4 · 12 minNemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 4 · 11 minHow to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 4 · 10 minEVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 4 · 14 minDesigning the hf CLI as an agent-optimized way to work with the Hub00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 3 · 14 minDirect Preference Optimization Beyond Chatbots00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 3 · 10 minAdding MCP Tools to Reachy Mini00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 2 · 5 minHolo3.1: Fast & Local Computer Use Agents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 1 · 4 minIntroducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 1 · 10 minBeyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jun 1 · 10 minWelcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 29 · 24 minProfiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 27 · 5 minITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 27 · 19 minShipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 27 · 9 minReachy Mini goes fully local00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 25 · 10 minHarness, Scaffold, and the AI Agent Terms Worth Getting Right00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 23 · 7 minTowards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 22 · 13 minSpecialization Beats Scale: A Strategic Variable Most AI Procurement Decisions Overlook00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 19 · 5 minOlmoEarth v1.1: A more efficient family of models00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 19 · 29 minIntroducing the Ettin Reranker Family00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 18 · 13 minFine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 18 · 5 minPaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 18 · 9 minThe Open Agent Leaderboard00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 14 · 17 minGranite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 14 · 19 minUnlocking asynchronicity in continuous batching00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 11 · 20 minBuilding Blocks for Foundation Model Training and Inference on AWS00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 10 · 6 minMachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 9 · 14 min"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 8 · 9 minCyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 8 · 9 minEMO: Pretraining mixture of experts for emergent modularity00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 8 · 8 minMedQA: Fine-Tuning a Clinical AI on AMD ROCm — No CUDA Required00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 6 · 8 minvLLM V0 to V1: Correctness Before Corrections in RL00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · May 6 · 7 minAdding Benchmaxxer Repellant to the Open ASR Leaderboard00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 29 · 18 minAI evals are becoming the new compute bottleneck00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 29 · 14 minGranite 4.1 LLMs: How They’re Built00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 29 · 5 minDeepInfra on Hugging Face Inference Providers 🔥00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 28 · 16 minIntroducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 28 · 5 minAdaptive Ultrasound Imaging with Physics-Informed NV-Raw2Insights-US AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 27 · 8 minHow to build scalable web apps with OpenAI's Privacy Filter00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 24 · 8 minDeepSeek-V4: a million-token context that agents can actually use00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 23 · 9 minHow to Use Transformers.js in a Chrome Extension00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 22 · 8 minGemma 4 VLA Demo on Jetson Orin Nano Super00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 21 · 9 minQIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 21 · 8 minHow to Ground a Korean AI Agent in Real Demographics with Synthetic Personas00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 21 · 6 minAI and the Future of Cybersecurity: Why Openness Matters00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 17 · 12 minBuilding a Fast Multilingual OCR Model with Synthetic Data00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 16 · 12 minThe PR you would have opened yourself00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 16 · 12 minEcom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 16 · 18 minTraining and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 15 · 15 minInside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 15 · 3 minMeet HoloTab by HCompany. Your AI browser companion. 00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 9 · 5 minWaypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 9 · 15 minMultimodal Embedding & Reranker Models with Sentence Transformers00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 8 · 6 minALTK‑Evolve: On‑the‑Job Learning for AI Agents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 8 · 4 minSafetensors is Joining the PyTorch Foundation00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 2 · 26 minWelcome Gemma 4: Frontier multimodal intelligence on device00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 1 · 4 minHolo3: Breaking the Computer Use Frontier00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Apr 1 · 6 minAny Custom Frontend with Gradio's Backend00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 31 · 7 minGranite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 31 · 30 minTraining mRNA Language Models Across 25 Species for $16500 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 31 · 16 minTRL v1.0: Post-Training Library That Holds When the Field Invalidates Its Own Assumptions00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 24 · 10 minA New Framework for Evaluating Voice Agents (EVA)00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 20 · 13 minBuild a Domain-Specific Embedding Model in Under a Day00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 20 · 3 minWhat's New in Mellea 0.4.0 + Granite Libraries Release00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 19 · 11 min**Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding**00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 17 · 8 minNemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 17 · 13 minState of Open Source on Hugging Face: Spring 202600 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 17 · 5 minHolotron-12B - High Throughput Computer Use Agent00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 16 · 5 minThe First Healthcare Robotics Dataset and Foundational Physical AI Models for Healthcare Robotics00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 13 · 8 minBeyond Semantic Similarity: Introducing NVIDIA NeMo Retriever’s Generalizable Agentic Retrieval Pipeline00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 13 · 10 minBuild an Agent That Thinks Like a Data Scientist: How We Hit #1 on DABStep with Reusable Tool Generation00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 12 · 9 minHow NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II 00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 11 · 4 minCode Concepts: A Large-Scale Synthetic Dataset Generated from Programming Concept Seeds00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 10 · 8 minHow NVIDIA Builds Open Data for AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 10 · 7 minIntroducing Storage Buckets on the Hugging Face Hub00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 10 · 30 minKeep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 9 · 2 minGranite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 9 · 10 minLeRobot v0.5.0: Scaling Every Dimension00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 9 · 15 minUlysses Sequence Parallelism: Training with Million-Token Contexts00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 6 · 7 minConversational LLM Evaluations in Minutes with NVIDIA NeMo Evaluator Agent Skills 00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 5 · 9 minBringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 5 · 9 minIntroducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Mar 3 · 8 minPRX Part 3 — Training a Text-to-Image Model in 24h!00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 26 · 10 minMixture of Experts (MoEs) in Transformers00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 24 · 8 minDeploying Open Source Vision Language Models (VLM) on Jetson00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 20 · 5 minTrain AI models with Unsloth and Hugging Face Jobs for FREE00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 20 · 4 minGGML and llama.cpp join HF to ensure the long-term progress of Local AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 19 · 2 min「データ不足」の壁を越える：合成ペルソナが日本のAI開発を加速00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 18 · 11 minIBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 18 · 4 minOne-Shot Any Web App with Gradio's gr.HTML00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 17 · 2 minNVIDIA Nemotron 2 Nano 9B Japanese: 日本のソブリンAIを支える最先端小規模言語モデル00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 13 · 9 minCustom Kernels for All from Codex and Claude00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 12 · 8 minOpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 9 · 6 minTransformers.js v4 Preview: Now Available on NPM!00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 5 · 4 minIntroducing SyGra Studio00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 4 · 5 minNemotron ColEmbed V2: Raising the Bar for Multimodal Retrieval with ViDoRe V3’s Top Model00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 4 · 4 minCommunity Evals: Because we're done trusting black-box leaderboards over the community00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 3 · 2 minH Company's new Holo2 model takes the lead in UI Localization00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 3 · 8 minThe Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Feb 3 · 30 minTraining Design for Text-to-Image Models: Lessons from Ablations00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 29 · 7 minIntroducing NVIDIA Cosmos Policy for Advanced Robot Control00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 29 · 8 minIntroducing Daggr: Chain apps programmatically, inspect visually00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 28 · 5 minNemotron-Personas-Brazil: Co-Designed Data for Sovereign AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 28 · 10 minWe Got Claude to Build CUDA Kernels and teach open models!00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 27 · 6 minArchitectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek 00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 27 · 8 minAlyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 27 · 16 minUnlocking Agentic RL Training for GPT-OSS: A Practical Retrospective00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 26 · 4 min**NVIDIA Earth-2 Open Models Span the Whole Weather Stack**00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 21 · 6 minAssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 20 · 8 minOne Year Since the “DeepSeek Moment”00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 20 · 14 minDifferential Transformer V200 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 20 · 4 minIntroducing Waypoint-1: Real-time interactive video diffusion from Overworld00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 15 · 2 minIntroducing OptiMind, a research model designed for optimization00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 15 · 6 minOpen Responses: What you need to know00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 6 · 7 minSmall Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models 00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 5 · 6 minNVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 5 · 9 minIntroducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Jan 5 · 11 minNVIDIA brings agents to life with DGX Spark and Reachy Mini00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Dec 23 · 10 minAprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Dec 18 · 15 minTokenization in Transformers v5: Simpler, Clearer, and More Modular00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Dec 17 · 12 minThe Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Dec 15 · 5 minCUGA on Hugging Face: Democratizing Configurable AI Agents00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Dec 11 · 9 minNew in llama.cpp: Model Management00 repliesSaveShare
ArticleHugging Face Blog@hugging-face-blog · Dec 11 · 13 minCodex is Open Sourcing AI models00 repliesSaveShare
