As part of our longstanding partnership with Amazon Bedrock, we are pleased to announce the addition of our latest and most advanced Foundation Model, Jamba-Instruct, to AI21 Labs’ offering on Amazon Bedrock. 

‍Due to its 256K context window and competitive pricing, Jamba-Instruct is the economic choice for companies looking to solve lengthy document summarization, question answering, and text generation tasks. 

‍By offering Jamba-Instruct on Amazon Bedrock, a fully managed service utilized by the world’s top companies to build and deploy generative AI applications, we are meeting enterprises where they are with technology that is purpose-built for their needs.

‍We look forward to what enterprises will build with Jamba-Instruct on Amazon Bedrock.

Jamba-Instruct: Built from hybrid SSM-Transformer architecture

‍As the world’s first production-grade SSM-Transformer model, Jamba-Instruct is built from the groundbreaking Jamba architecture, a novel blocks-and-layers approach that successfully integrates SSM architecture with the conventional Transformer architecture.

‍Jamba-Instruct leverages its hybrid architecture to achieve leading performance, quality, and cost efficiency. As a result, it is ideal for enterprises who wish to build and scale reliable GenAI workflows, without running into the common barrier of prohibitive compute costs. 

‍Jamba-Instruct stands out for its:

  • Impressive context window length: Offering a 256K context window, Jamba-Instruct supports a range of GenAI enterprise use cases, such as enhancing the retrieval stage of a RAG pipeline, summarizing lengthy documents, and offering more comprehensive synthesis over multiple documents.  
  • Cost-efficient processing: Due to its novel hybrid architecture, Jamba-Instruct handles lengthy context on a smaller cloud footprint than ever before, driving down costs.
  • Best value per cost: Surpassing or rivaling competitors across common quality benchmarks, Jamba-Instruct’s highly competitive pricing gives enterprises the best value for their money.
Graph

Scalable and secure infrastructure

‍On Amazon Bedrock, enterprises can harness the value of state-of-the-art language models like Jamba-Instruct, all within the trusted, scalable environment of AWS. 

‍As a fully managed service, clients focus exclusively on building the high-impact applications they envision, removing the need to spend time maintaining infrastructure and accelerating the time to deployment. And with a robust offering of VPC settings, encryption tools, and compliance monitoring, companies can ensure they are building securely, safely, and responsibly. 

Getting started

‍To start building with Jamba-Instruct on Amazon Bedrock, enter the Amazon Bedrock console, navigate to Model access, and select Jamba-Instruct. 

‍Build your next GenAI enterprise application with state-of-the-art language models from AI21 Labs on Amazon Bedrock.