📰 Hugging Face Blog

olmo-eval: An evaluation workbench for the model development loop

Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP

Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech

Introducing North Mini Code: Cohere’s First Model For Developers

How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces

NeuroBait: I fine-tuned a model to spark dopamine for ADHD brain

Migrating Your GitHub CI to Hugging Face Jobs

The Open Source Community is backing OpenEnv for Agentic RL

Amazing Digital Dentures (a failed project)

Five labs, five minds: building a multi-model finance drama on small models

Job Searcher

Thousand Token Wood: shipping a multi-agent economy on a 3B model

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios

Designing the hf CLI as an agent-optimized way to work with the Hub

Direct Preference Optimization Beyond Chatbots

Adding MCP Tools to Reachy Mini

Holo3.1: Fast & Local Computer Use Agents

Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM