AI Automation

Learn how deep research agents can be optimized through context engineering and agent harness design to improve LLM performance and reduce token use.

Explore how Transformers v5 shifts to full PyTorch support, simplifies AI modeling, enhances training, inference, and makes quantization first-class.

Learn how Claude fine-tunes open-source LLMs with Hugging Face Skills, handles GPU jobs, and simplifies AI training for developers.

Join the AMD Open Robotics Hackathon 2025 in Tokyo or Paris. Build AI-powered robots with LeRobot, win prizes, and push real-world innovation.

Explore how China’s AI chip innovation is challenging NVIDIA, reshaping global compute, and driving the open-source model revolution.

Can you distill efficient reasoning into existing LLMs using task-specific data? Discover how Apriel-H1 achieves 2.1x throughput with minimal quality loss.

Explore trends in the Open ASR Leaderboard, from LLM-boosted models to multilingual & long-form transcription accuracy vs speed tradeoffs.

Fine-tune TRL models 20x faster with RapidFire AI using adaptive scheduling, multi-GPU support, and live control. Maximize throughput & model accuracy.

Learn to build ROCm kernels using Hugging Face tools. Streamline development, integrate with PyTorch, and deploy with ease to the community Hub.

Explore how AnyLanguageModel simplifies working with local and remote LLMs on Apple platforms—and how it compares to Foundation Models.