AI21 Labs' Jamba-Instruct model now available in Amazon Bedrock
AI21 Labs’ Jamba-Instruct, a powerful instruction-following large language model, is now available in Amazon Bedrock. Fine-tuned for instruction following and built for reliable commercial use, Jamba-Instruct can engage in open-ended dialogue, understand context and subtext, and complete a wide variety of tasks based on natural language instructions.
With its 256K context window, Jamba-Instruct has the capability to ingest the equivalent of a 800-page novel or an entire company's financial filings for a given fiscal year. This large context window allows Jamba-Instruct to answer questions and produce summaries that are grounded in the provided inputs, eliminating the need for manual segmentation of documents in order to fit smaller context windows.
With its strong reasoning and analysis capabilities, Jamba-Instruct can break down complex problems, gather relevant information, and provide structured outputs. The model is ideal for common enterprise use cases such as enabling Q&A on call transcripts, summarizing key points from documents, building chatbots, and more. Whether you need assistance with coding, writing, research, analysis, creative tasks, or general task assistance, Jamba-Instruct is a powerful model that can streamline your workflow and accelerate time to production for your gen AI enterprise applications.
AI21 Labs’ Jamba-Instruct foundation model is now available in Amazon Bedrock in the US East (N. Virginia) AWS region. To learn more read the Machine Learning blog, visit the AI21 Labs in Amazon Bedrock product page, and documentation. To get started with Jamba-Instruct in Amazon Bedrock, visit the Amazon Bedrock console.