Remove LLM Remove ML Engineer Remove Responsible AI
article thumbnail

Track LLM model evaluation using Amazon SageMaker managed MLflow and FMEval

AWS Machine Learning Blog

Evaluating large language models (LLMs) is crucial as LLM-based systems become increasingly powerful and relevant in our society. Rigorous testing allows us to understand an LLMs capabilities, limitations, and potential biases, and provide actionable feedback to identify and mitigate risk.

LLM 113
article thumbnail

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

AWS Machine Learning Blog

This combination makes achieving low latency a challenge for use cases such as real-time text completion, simultaneous translation, or conversational voice assistants, where subsecond response times are critical. With Medusa-1, the predictions are identical to those of the originally fine-tuned LLM. In this post, we focus on Medusa-1.

LLM 77
professionals

Sign Up for our Newsletter

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

article thumbnail

Top Artificial Intelligence AI Courses from Google

Marktechpost

Introduction to AI and Machine Learning on Google Cloud This course introduces Google Cloud’s AI and ML offerings for predictive and generative projects, covering technologies, products, and tools across the data-to-AI lifecycle. It also introduces Google’s 7 AI principles.

article thumbnail

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

AWS Machine Learning Blog

Machine learning (ML) engineers must make trade-offs and prioritize the most important factors for their specific use case and business requirements. Responsible AI Implementing responsible AI practices is crucial for maintaining ethical and safe deployment of RAG systems.

article thumbnail

Map Earth’s vegetation in under 20 minutes with Amazon SageMaker

AWS Machine Learning Blog

Amazon SageMaker supports geospatial machine learning (ML) capabilities, allowing data scientists and ML engineers to build, train, and deploy ML models using geospatial data. His current area of research includes LLM evaluation and data generation. About the Author Xiong Zhou is a Senior Applied Scientist at AWS.

article thumbnail

Accelerating ML experimentation with enhanced security: AWS PrivateLink support for Amazon SageMaker with MLflow

AWS Machine Learning Blog

MLflow , a popular open-source tool, helps data scientists organize, track, and analyze ML and generative AI experiments, making it easier to reproduce and compare results. Amazon SageMaker with MLflow is a capability in SageMaker that enables users to create, manage, analyze, and compare their ML experiments seamlessly.

ML 103
article thumbnail

The journey of PGA TOUR’s generative AI virtual assistant, from concept to development to prototype

AWS Machine Learning Blog

We formulated a text-to-SQL approach where by a user’s natural language query is converted to a SQL statement using an LLM. This data is again provided to an LLM, which is asked to answer the user’s query given the data. The relevant information is then provided to the LLM for final response generation.