Announcing 1-Click Models powered by Hugging Face on DigitalOcean

We’re excited to announce that DigitalOcean now offers 1-click Model deployment powered by Hugging Face. Affectionately known as HUGS on DO, this new inference solution provides deployable, popular, third party generative AI models, optimized to run on DigitalOcean GPU Droplets. With 1-Click Models, users can now launch AI applications faster and more efficiently than ever before, combining DigitalOcean’s signature simplicity with Hugging Face’s widely used platform.

Hugging Face is the leading open platform for AI builders. They empower the next generation of machine learning engineers, scientists, and end users to collaborate, innovate, and shape an open and ethical AI future. With the fast-growing community, some of the most used open-source ML libraries and tools, and a talented science team exploring the edge of tech, Hugging Face is at the heart of the AI revolution.

Your shortcut to AI Innovation

1-Click Models provide a user-friendly solution that allows you to get up and running within minutes. With our new partnership, Hugging Face users can now deploy the most popular models directly on DigitalOcean GPU Droplets. By simply selecting a model on Hugging Face and selecting DigitalOcean from the “Deploy” dropdown, users can start building with a dedicated inference endpoint immediately on DigitalOcean. Users can also deploy 1-Click Models directly from the DigitalOcean cloud console. This ease of use reflects our ongoing commitment to simplifying the developer experience.

Key Features

• 1-click deployable models: Deploy popular AI models like Llama 3 by Meta and Mistral with just one click on GPU Droplets powered by NVIDIA H100s accelerated computing.
• Simplified Setup: Utilizing 1-Click Models on DigitalOcean removes infrastructure complexities, allowing you to focus on building with model endpoints immediately without the need for complex setup or software configurations.
• Optimized Performance: 1-Click Models are end-to-end optimized to run on high-performance GPU Droplets, ensuring models run on cutting-edge DigitalOcean hardware with minimal overhead.
• Fast Time-to-Value: Customers can start querying model inference endpoints within minutes, not days, compared to solutions requiring extensive configuration.
• Partnership with Hugging Face: Models are maintained and updated by Hugging Face, helping to ensure that customers have access to fully tested optimizations and the latest versions and features when creating new model endpoints.

1-Click Models powered by Hugging Face on DigitalOcean

• meta-llama/Meta-Llama-3.1-8B-Instruct
• meta-llama/Meta-Llama-3.1-70B-Instruct
• meta-llama/Meta-Llama-3.1-405B-Instruct-FP8
• Qwen/Qwen2.5-7B-Instruct
• google/gemma-2-9b-it
• google/gemma-2-27b-it
• mistralai/Mixtral-8x7B-Instruct-v0.1
• mistralai/Mistral-7B-Instruct-v0.3
• mistralai/Mixtral-8x22B-Instruct-v0.1
• NousResearch/Hermes-3-Llama-3.1-8B
• NousResearch/Hermes-3-Llama-3.1-70B
• NousResearch/Hermes-3-Llama-3.1-405B
• NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO

Deploying 1-Click Models on DO

1-Click Models powered by Hugging Face on DigitalOcean offer a solution for developers looking to deploy popular AI/ML models. With just one click, users can skip the usual setup headaches and dive straight into building innovative applications on GPU Droplets. Whether you’re a developer, AI/ML engineer, or researcher, 1-Click Models give you the performance and flexibility you need to make your ideas come to life.

Try a 1-click model today and experience the simplicity of HUGS on DO ->