Baseten is now a supported Inference Provider on the Hugging Face Hub, allowing users to access Baseten-hosted models via standard HF interfaces. The integration passes through provider costs without markup, and PRO users receive $2 in monthly credits usable across all providers.
Model Hosting
模型托管
Deploying trained models on cloud servers for real-time inference and access.
Curated Intelligence
Hugging Face Hub has integrated FriendliAI's inference infrastructure as an option in the 'Deploy this model' button. This partnership aims to simplify and accelerate generative AI model serving, though specific performance benchmarks and cost-efficiency metrics are not detailed.
Hugging Face introduced the Private Hub, enabling enterprises to store machine learning models and code in private environments. This feature addresses data privacy and compliance needs by supporting AI development within isolated networks.
Hugging Face announced the integration of Stable-Baselines3, a leading Deep Reinforcement Learning library, into its Hub. Users can now host, share, and load community-trained RL agents via the huggingface_sb3 package, streamlining model versioning and collaboration for reinforcement learning workflows.