Remove en about-us attractions
article thumbnail

Advanced RAG patterns on Amazon SageMaker

AWS Machine Learning Blog

This post discusses RAG patterns to improve response accuracy using LangChain and tools such as the parent document retriever in addition to techniques like contextual compression in order to enable developers to improve existing generative AI applications. We use an ml.t3.medium For step-by-step instructions, refer to the GitHub repo.

AWS 106
article thumbnail

Meet the winners of the Research Rovers: AI Research Assistants for NASA Challenge

DrivenData Labs

LLMs were also the key component in chatbot features of several submissions, allowing users to ask questions about a specific paper of interest. bge-small-en-v1.5 When we came across the NASA competition, we instantly recognized how it aligned with our values and the expertise each of us brings to the table.

AI 147
professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Fine-tune Llama 2 for text generation on Amazon SageMaker JumpStart

AWS Machine Learning Blog

Regardless of which version of the model a developer uses, the responsible use guide from Meta can assist in guiding additional fine-tuning that may be necessary to customize and optimize the models with appropriate safety mitigations. For more information about version updates, refer to Shut down and Update Studio Apps.

ML 92
article thumbnail

A 50-Year Quest: My Personal Journey with the Second Law of Thermodynamics

Hacker News

This is part 2 in a 3-part series about the Second Law: 1. Building on an earlier interest in space and spacecraft , I’d gotten very interested in physics, and was trying to read everything I could about it. But one afternoon late that summer I decided I should really find out what that mysterious fifth book was all about.

article thumbnail

Multi-Modal Methods: Visual Speech Recognition (Lip Reading)

ML Review

In our previous work , we briefly attempted to outline Computer Vision’s claim on intelligence; building systems that can learn, infer and reason about the world from visual data alone. Regardless of application, the tricks and knowledge gathered on architectures and loss functions may be repurposed and used anew somewhere else.