Today, AWS announces the general availability of Custom Model Import, which allows customers to import and use their customized models alongside existing foundation models via a single, unified API.
You can now import custom weights for a variety of supported model architectures (such as Meta Llama 3.2 and Mixtral 8x7B) without the overhead of model lifecycle and infrastructure management. Now, customers can access their imported custom models in an on-demand serverless manner without having to manage instances. They can accelerate generative AI application development by integrating their imported custom models seamlessly with native Bedrock tools and features like Agents, Knowledge Bases, Guardrails, Prompt Flows, and more.
Amazon Bedrock Custom Model Import is generally available in the US-East (N. Virginia) and US-West (Oregon) AWS regions. You can get started by initiating the model import workflow in the custom models page of the Amazon Bedrock console. To learn more read the AWS Machine Learning Blog, Bedrock Custom Model Import page, or visit the documentation page.
Source:: Amazon AWS