End-to-end LLM training on instance clusters with over 100 nodes using AWS Trainium
Llama is Meta AI’s large language model (LLM), with variants ranging from […]
Read moreCategory: Machine learning
Enhance image search experiences with Amazon Personalize, Amazon OpenSearch Service, and Amazon Titan Multimodal Embeddings in Amazon Bedrock
A variety of different techniques have been used for returning images relevant […]
Read more
Fine-tune large multimodal models using Amazon SageMaker
Large multimodal models (LMMs) integrate multiple data types into a single model. […]
Read more
Accelerate Mixtral 8x7B pre-training with expert parallelism on Amazon SageMaker
Mixture of Experts (MoE) architectures for large language models (LLMs) have recently […]
Read more
Generating fashion product descriptions by fine-tuning a vision-language model with SageMaker and Amazon Bedrock
In the world of online retail, creating high-quality product descriptions for millions […]
Read more
Create a multimodal assistant with advanced RAG and Amazon Bedrock
Retrieval Augmented Generation (RAG) models have emerged as a promising approach to […]
Read more
Efficient and cost-effective multi-tenant LoRA serving with Amazon SageMaker
In the rapidly evolving landscape of artificial intelligence (AI), the rise of […]
Read more
How 20 Minutes empowers journalists and boosts audience engagement with generative AI on Amazon Bedrock
This post is co-written with Aurélien Capdecomme and Bertrand d’Aure from 20 […]
Read more
Building Generative AI prompt chaining workflows with human in the loop
Generative AI is a type of artificial intelligence (AI) that can be […]
Read more
Mixtral 8x22B is now available in Amazon SageMaker JumpStart
Today, we are excited to announce the Mixtral-8x22B large language model (LLM), […]
Read more