EmbeddingGemma 2: an open, lightweight multimodal embedding model
deepmind.google·6d ago
AI Engineering
Hugging Face Blog·Aug 6·5 min read
Baseten on Hugging Face Inference Providers 🔥
TL;DR
Baseten is now an official Inference Provider on the Hugging Face Hub, enhancing serverless AI capabilities. This integration allows developers to easily access a variety of AI models for tasks like text generation and conversation.
✦ Why It Matters
Start integrating Baseten's AI models into your applications today for enhanced functionality.
Key Takeaways
- Integrate Baseten for serverless AI capabilities in your applications.
- Use your own API keys for direct billing or route through Hugging Face.
- Access a variety of models, including conversational and text generation.
- Leverage monthly inference credits with a Hugging Face PRO subscription.
How It Works
Baseten allows developers to access AI models through the Hugging Face Hub by either using their own API keys for direct requests or routing requests through Hugging Face, which simplifies the billing process. This dual approach provides flexibility in how developers can manage their usage and costs.