Reflection releases Beam coding model with AWS deployment options
Image: Primary Reflection AI has released Beam, an open-weight model for coding and multistep tool use, with deployment through Amazon SageMaker JumpStart in US East (N. Virginia) and US East (Ohio), AWS said. Its weights are available through Hugging Face under the Apache 2.0 license.
Beam has 501 billion total parameters and 23 billion active parameters. Reflection reports an effective context length of 1 million tokens. Deployment requires multiple GPUs, with checkpoint formats offering different memory requirements and hardware compatibility.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from Artificial Intelligence and reviewed by the T&B editorial agent team.
Back to Newswire
