Jamba-Instruct, the instruction-following large language model developed by AI21Labs is now available in Amazon Bedrock. Built for reliable commercial use Jamba-Instruct is a boon for Amazon's customers.

Yet another model has been added to Amazon Bedrock, the fully managed service on the AWS platform that provides access to a variety of foundation models (FMs) from leading AI companies, substantially increasing its abilities for building generative AI applications.

AWS  already has large pool of leading models such as AI21 Labs' Jurassic, Cohere's Command and Embed, Meta's Llama 2, Stability AI's Stable Diffusion, as well as Amazon's own Titan models, each of which is fine-tuned for specific purposes. For instance Claude 3 Opus, the most intelligent Claude 3 model, with best-in-market performance on highly complex tasks can do both text as well as image generation and is useful in domains such as:

• Task automation: planning and execution of complex actions across APIs, databases, and interactive coding
• Research: brainstorming and hypothesis generation, research review, and drug discovery
• Strategy: advanced analysis of charts and graphs, financials and market trends, and forecasting

The new addition of Jamba-Instruct further enhances Bedrock with some of the most common use cases enterprises can encounter, such as enabling accurate QA (question answering) on earnings call transcripts, thoroughly summarizing key points from legal documents, or building chatbots that can coherently sustain long and reference-based conversations with customers. All possible thanks to its 256K context window that allows it, for instance, to ingest the equivalent of a 800-page novel or an entire company's financial filings for a given fiscal year.

For example, it would be suitable for detecting contradictions between different documents or analyzing one document in the context of another. The following is an example prompt suitable for this use case:

You are an expert research assistant;
you are to note any contradictions between the first document and second document provided:

Document 1:
{the document content}

Document 2:
{the document content}

The model isn't targeted only at business users. It will also be useful to developers using Amazon Bedrock and AWS SDK for Python (Boto3).

More Information

AI21 Labs in Amazon Bedrock

Related Articles

 Amazon Bedrock Adds Support For Anthropic's Claude3 Opus