Fine-tune LLMs with synthetic data for context-based Q&A using Amazon Bedrock

There’s a growing demand from customers to incorporate generative AI into their businesses. Many use cases involve using pre-trained large language models (LLMs) through approaches like Retrieval Augmented Generation (RAG). However, for advanced, domain-specific tasks or those requiring specific formats, model customization techniques such as fine-tuning are sometimes necessary. Amazon Bedrock provides you with the […]

Achieve ~2x speed-up in LLM inference with Medusa-1 on Amazon SageMaker AI

This blog post is co-written with Moran beladev, Manos Stergiadis, and Ilya Gusev from Booking.com. Large language models (LLMs) have revolutionized the field of natural language processing with their ability to understand and generate humanlike text. Trained on broad, generic datasets spanning a wide range of topics and domains, LLMs use their parametric knowledge to […]

LLM-as-a-judge on Amazon Bedrock Model Evaluation

The evaluation of large language model (LLM) performance, particularly in response to a variety of prompts, is crucial for organizations aiming to harness the full potential of this rapidly evolving technology. The introduction of an LLM-as-a-judge framework represents a significant step forward in simplifying and streamlining the model evaluation process. This approach allows organizations to […]

From concept to reality: Navigating the Journey of RAG from proof of concept to production

Generative AI has emerged as a transformative force, captivating industries with its potential to create, innovate, and solve complex problems. However, the journey from a proof of concept to a production-ready application comes with challenges and opportunities. Moving from proof of concept to production is about creating scalable, reliable, and impactful solutions that can drive […]