Author: Nick McCarthy

Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost per correct answer, agent trajectory cost, and rubric-graded deliverable quality across OpenAI models on Amazon Bedrock.

Deploy a customer-operated LiteLLM gateway on Amazon ECS with AWS Fargate, connect it to an OpenAI model on Amazon Bedrock, and configure Codex to route requests through the gateway’s Responses API with scoped identities, budgets, rate limits, and telemetry. We also compare direct IAM Identity Center access and a managed Portkey deployment.

In this post, we explore where RFT is most effective, using the GSM8K mathematical reasoning dataset as a concrete example. We then walk through best practices for dataset preparation and reward function design, show how to monitor training progress using Amazon Bedrock metrics, and conclude with practical hyperparameter tuning guidelines informed by experiments across multiple models and use cases.

In this post, we’ll explore how Atos used the AWS AI League to help accelerate AI education across 400+ participants, highlight the tangible benefits of gamified, experiential learning, and share actionable insights you can apply to your own AI enablement programs.

You can now achieve significant performance improvements when using Amazon Bedrock Custom Model Import, with reduced end-to-end latency, faster time-to-first-token, and improved throughput through advanced PyTorch compilation and CUDA graph optimizations. With Amazon Bedrock Custom Model Import you can to bring your own foundation models to Amazon Bedrock for deployment and inference at scale. In this post, we introduce how to use the improvements in Amazon Bedrock Custom Model Import.

In this post, we demonstrate that fine-tuning VLMs provides a powerful and flexible approach to automate and significantly enhance document understanding capabilities. We also demonstrate that using focused fine-tuning allows smaller, multi-modal models to compete effectively with much larger counterparts (98% accuracy with Qwen2.5 VL 3B).

February 2024: This post was reviewed and updated for accuracy. This post is co-written with Thatcher Thornberry from bpx energy.  Facies classification is the process of segmenting lithologic formations from geologic data at the wellbore location. During drilling, wireline logs are obtained, which have depth-dependent geologic information. Geologists are deployed to analyze this log data […]

One of the most exciting AWS re:Invent 2020 announcements was a new Amazon SageMaker feature, purpose built to help detect bias in machine learning (ML) models and explain model predictions: Amazon SageMaker Clarify. In today’s world where predictions are made by ML algorithms at scale, it’s increasingly important for large tech organizations to be able […]