Tag: question answering
Breaking News
Mixtral-8x7B is now available in Amazon SageMaker JumpStart | Amazon Web Services
Today, we are excited to announce that the Mixtral-8x7B large language model (LLM), developed by Mistral AI, is available for customers through Amazon SageMaker...
Deploy foundation models with Amazon SageMaker, iterate and monitor with TruEra | Amazon Web Services
This blog is co-written with Josh Reini, Shayak Sen and Anupam Datta from TruEra Amazon SageMaker JumpStart provides a variety of pretrained foundation models...
Frugality meets Accuracy: Cost-efficient training of GPT NeoX and Pythia models with AWS Trainium | Amazon Web Services
Large language models (or LLMs) have become a topic of daily conversations. Their quick adoption is evident by the amount of time required to...
Mitigate hallucinations through Retrieval Augmented Generation using Pinecone vector database & Llama-2 from Amazon SageMaker JumpStart | Amazon Web Services
Despite the seemingly unstoppable adoption of LLMs across industries, they are one component of a broader technology ecosystem that is powering the new AI...
Boosting RAG-based intelligent document assistants using entity extraction, SQL querying, and agents with Amazon Bedrock | Amazon Web Services
Conversational AI has come a long way in recent years thanks to the rapid developments in generative AI, especially the performance improvements of large...
This Week’s Awesome Tech Stories From Around the Web (Through December 2)
When AI Unplugs, All Bets Are OffMatthew Smith | IEEE Spectrum“The next great chatbot will run at lighting speed on your laptop PC—no internet...
Evaluate large language models for quality and responsibility | Amazon Web Services
The risks associated with generative AI have been well-publicized. Toxicity, bias, escaped PII, and hallucinations negatively impact an organization’s reputation and damage customer trust....
Operationalize LLM Evaluation at Scale using Amazon SageMaker Clarify and MLOps services | Amazon Web Services
In the last few years Large Language Models (LLMs) have risen to prominence as outstanding tools capable of understanding, generating and manipulating text with...
Simplify data prep for generative AI with Amazon SageMaker Data Wrangler | Amazon Web Services
Generative artificial intelligence (generative AI) models have demonstrated impressive capabilities in generating high-quality text, images, and other content. However, these models require massive amounts...
Build a contextual chatbot for financial services using Amazon SageMaker JumpStart, Llama 2 and Amazon OpenSearch Serverless with Vector Engine | Amazon Web Services
The financial service (FinServ) industry has unique generative AI requirements related to domain-specific data, data security, regulatory controls, and industry compliance standards. In addition,...
Text embedding and sentence similarity retrieval at scale with Amazon SageMaker JumpStart | Amazon Web Services
Text vectors or embeddings are numerical vector representations of text that are generated by large language models (LLMs). After LLMs are fully pre-trained on...
Amazon Textract’s new Layout feature introduces efficiencies in general purpose and generative AI document processing tasks | Amazon Web Services
Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from any document or image. AnalyzeDocument Layout is a...