AWS Machine Learning Blog

APRIL 8, 2024

Unlocking accurate and insightful answers from vast amounts of text is an exciting capability enabled by large language models (LLMs). When building LLM applications, it is often necessary to connect and query external data sources to provide relevant context to the model.

AWS 99

AWS Machine Learning Machine Learning Natural Language Processing 99

AWS Machine Learning Blog

DECEMBER 14, 2023

Retrieval Augmented Generation (RAG) is a process in which a language model retrieves contextual documents from an external data source and uses this information to generate more accurate and informative text. In this post, we demonstrate how to harness the power of RAG to enhance the prompts sent to your Stable Diffusion models.

AWS 94

AWS Natural Language Processing Database ML 94

Snorkel AI

SEPTEMBER 20, 2023

Corporate leaders soon urged data science teams to use large language models (LLMs), and data science teams turned to fine-tuning and retrieval-augmented generation (RAG) to mitigate generative AI (genAI) shortcomings. Neither fine-tuning nor RAG requires excluding the other, and the two approaches work better together.

Data Science 59

Data Science Artificial Intelligence Artificial Intelligence Database 59

DagsHub

APRIL 1, 2024

Introduction Large language models (LLMs) such as GPT-3.5 Well, the ability of LLMs to produce high-level output lies in their embeddings. Their ability to store rich representations of textual information allows LLM to produce high-level contextual outputs. Fine-tuning as a strategy to improve embedding models.

Natural Language Processing 52

Natural Language Processing Data Preparation Algorithm AI 52

ODSC - Open Data Science

FEBRUARY 6, 2024

Check out some of the LLM-focused training sessions, workshops, and talks you’ll find at the conference. NLP with GPT-4 and other LLMs: From Training to Deployment with Hugging Face and PyTorch Lightning Dr. Jon Krohn | Chief Data Scientist | Nebula.io

Big Data Analytics 52

Big Data Analytics Big Data Analytics Big Data Big Data 52

AWS Machine Learning Blog

SEPTEMBER 1, 2023

Nowadays, the majority of our customers is excited about large language models (LLMs) and thinking how generative AI could transform their business. Furthermore, we deep dive on the most common generative AI use case of text-to-text applications and LLM operations (LLMOps), a subset of FMOps.

AI 103

AI AI ML ML 103

AWS Machine Learning Blog

JANUARY 26, 2024

Generative artificial intelligence (AI) applications built around large language models (LLMs) have demonstrated the potential to create and accelerate economic value for businesses. This post provides three guided steps to architect risk management strategies while developing generative AI applications using LLMs.

AWS 122

AWS AI AI ML 122

ODSC - Open Data Science

MARCH 8, 2024

An implementation with CLIP and GPT-4-vision In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language understanding and generation tasks. Here are some key challenges faced by LLMs: Outdated Knowledge : LLMs lack real-time updates and may provide outdated information.

Azure 52

Azure Data Science AI AI 52

Towards AI

APRIL 1, 2024

A few days ago, Databricks open sourced DBRX, a massive general-purpose LLM that show incredible performance across different benchmarks. Databricks released both the baseline model DBRX Base as well as the intstruction fine-tuned one DBRX Instruct.

Machine Learning 73

Machine Learning Machine Learning AI AI 73

AWS Machine Learning Blog

MAY 2, 2023

Today, we announce the availability of sample notebooks that demonstrate question answering tasks using a Retrieval Augmented Generation (RAG)-based approach with large language models (LLMs) in Amazon SageMaker JumpStart. LLMs can store factual knowledge by training their parameters on a large corpus of natural language data.

Algorithm 74

Algorithm Machine Learning Machine Learning Natural Language Processing 74

AWS Machine Learning Blog

NOVEMBER 7, 2023

Furthermore, the cost to train new LLMs can prove prohibitive for many enterprise settings. However, it’s possible to cross-reference a model answer with the original specialized content, thereby avoiding the need to train a new LLM model, using Retrieval-Augmented Generation (RAG).

AWS 94

AWS AI AI Database 94

Snorkel AI

FEBRUARY 6, 2024

Alex Ratner spoke with Alex Taylor, Global Head of Emerging Technology at QBE Ventures at SnorkelAI’s Enterprise LLM Summit in January 2024. The pair explored the challenges and impact of AI in the enterprise—particularly in the insurance world—and the importance of amplifying subject matter experts in the loop.

Data Science 52

Data Science Machine Learning Machine Learning AI 52

Snorkel AI

FEBRUARY 6, 2024

Alex Ratner spoke with Alex Taylor, Global Head of Emerging Technology at QBE Ventures at SnorkelAI’s Enterprise LLM Summit in January 2024. The pair explored the challenges and impact of AI in the enterprise—particularly in the insurance world—and the importance of amplifying subject matter experts in the loop.

Data Science 52

Data Science Machine Learning Machine Learning AI 52

Women in Big Data

DECEMBER 13, 2023

We are hearing about NLP, LLMs, ChatGPT and Generative AI a lot ! The goal of the talk was to learn about the basics of NLP (Natural Language Processing), how NLP is done, what is LLM (Large Language Model), Generative AI and how you can drive your career around it. The event was part of the chapter’s technical talk series 2023.

Natural Language Processing 52

Natural Language Processing Big Data Big Data Computer Science 52

AWS Machine Learning Blog

NOVEMBER 27, 2023

Data preparation is important at multiple stages in Retrieval Augmented Generation ( RAG ) models. Further, we show how to preprocess a dataset for RAG. Specifically, we clean the data and create RAG artifacts to answer the questions about the content of the dataset. Clean data is important for good model performance.

Data Preparation 74

Data Preparation AI AI Database 74

Data Science Dojo

DECEMBER 6, 2023

In this blog, we are enhancing our Language Model (LLM) experience by adopting the Retrieval-Augmented Generation (RAG) approach! So, let’s get started! Common hallucinations in large language models The most common problem faced by state-of-the-art LLMs is that they produce inaccurate or hallucinated responses.

Database 370

Database Data Preparation Algorithm AI 370

AWS Machine Learning Blog

APRIL 3, 2024

Search engines and recommendation systems powered by generative AI can improve the product search experience exponentially by understanding natural language queries and returning more accurate results. The model uses correlations across modalities to improve performance on these tasks compared to individual modal embeddings.

K-nearest Neighbors 100

K-nearest Neighbors AWS Machine Learning Machine Learning 100

Flipboard

NOVEMBER 22, 2023

In addition, customers are looking for choices to select the most performant and cost-effective machine learning (ML) model and the ability to perform necessary customization (fine-tuning) to fit their business use cases. The LLM generated text, and the IR system retrieves relevant information from a knowledge base.

ML 124

ML ML AWS Machine Learning 124

AWS Machine Learning Blog

MAY 14, 2024

These models are pre-trained on massive datasets and, to sometimes fine-tuned with smaller sets of more task specific data. RLHF is a technique that combines rewards and comparisons, with human feedback to pre-train or fine-tune a machine learning (ML) model.

AWS 86

AWS AI AI Machine Learning 86

AWS Machine Learning Blog

MAY 13, 2024

In part 1 of this blog series, we discussed how a large language model (LLM) available on Amazon SageMaker JumpStart can be fine-tuned for the task of radiology report impression generation. When summarizing healthcare texts, pre-trained LLMs do not always achieve optimal performance.

AI 105

AI AI AWS ML 105

AWS Machine Learning Blog

MARCH 28, 2024

With the advancements being made with LLMs like the Mixtral-8x7B Instruct , derivative of architectures such as the mixture of experts (MoE) , customers are continuously looking for ways to improve the performance and accuracy of generative AI applications while allowing them to effectively use a wider range of closed and open source models.

AWS 111

AWS Machine Learning Machine Learning AI 111

AWS Machine Learning Blog

SEPTEMBER 27, 2023

The existing generative AI solutions for question answering are mainly based on Retrieval Augmented Generation (RAG). In this case, the question answering task works better by fine-tuning the LLM with the documents. To address these challenges, we present a new framework with RAG and fine-tuned LLMs.

AI 88

AI AI ML ML 88

AWS Machine Learning Blog

MAY 9, 2024

This post is co-written with Tom Famularo, Abhay Shah and Nicolette Kontor from Verisk. Verisk (Nasdaq: VRSK) is a leading data analytics and technology partner for the global insurance industry. The company is committed to ethical and responsible AI development, with human oversight and transparency.

AI 114

AI AI AWS Data Governance 114

AWS Machine Learning Blog

DECEMBER 6, 2023

Conversational AI has come a long way in recent years thanks to the rapid developments in generative AI, especially the performance improvements of large language models (LLMs) introduced by training techniques such as instruction fine-tuning and reinforcement learning from human feedback.

SQL 101

SQL AWS Database Analytics 101

AWS Machine Learning Blog

JANUARY 4, 2024

We are seeing numerous uses, including text generation, code generation, summarization, translation, chatbots, and more. One such area that is evolving is using natural language processing (NLP) to unlock new opportunities for accessing data through intuitive SQL queries. What percentage of customers are from each region?”

SQL 119

SQL Database AI AI 119

Flipboard

DECEMBER 6, 2023

Enterprises turn to Retrieval Augmented Generation (RAG) as a mainstream approach to building Q&A chatbots. Finally, we take a closer look at how the Q4 team used Amazon Bedrock and SQLDatabaseChain to implement a RAG-based solution with SQL generation. This post is co-written with Stanislav Yeshchenko from Q4 Inc.

SQL 130

SQL Database AWS Machine Learning 130

AWS Machine Learning Blog

SEPTEMBER 21, 2023

In particular, we provide practical best practices for different customization scenarios, including training models from scratch, fine-tuning with additional data using full or parameter-efficient techniques, Retrieval Augmented Generation (RAG), and prompt engineering.

AI 100

AI AI AWS Deep Learning 100

The MLOps Blog

MARCH 12, 2024

TL;DR LLMOps involves managing the entire lifecycle of Large Language Models (LLMs), including data and prompt management, model fine-tuning and evaluation, pipeline orchestration, and LLM deployment. Retrieval Augmented Generation (RAG) enables LLMs to extract and synthesize information like an advanced search engine.

Database 52

Database Machine Learning Machine Learning AI 52

AWS Machine Learning Blog

OCTOBER 24, 2023

In this post, we discuss how to extend a new or existing IDP architecture with large language models (LLMs). You can use LLMs in one or all phases of IDP depending on the use case and desired outcome. In this architecture, LLMs are used to perform specific tasks within the IDP workflow. However, the potential doesn’t end there.

Database 113

Database AWS ML ML 113

Flipboard

NOVEMBER 20, 2023

Retrieval Augmented Generation (RAG) allows you to provide a large language model (LLM) with access to data from external knowledge sources such as repositories, databases, and APIs without the need to fine-tune it. In this post, we demonstrate how to use Amazon SageMaker Studio to build a RAG question answering solution.

AWS 128

AWS Database Machine Learning Machine Learning 128

AWS Machine Learning Blog

SEPTEMBER 15, 2023

Large language model (LLM) agents are programs that extend the capabilities of standalone LLMs with 1) access to external tools (APIs, functions, webhooks, plugins, and so on), and 2) the ability to plan and execute tasks in a self-directed fashion. We conclude the post with items to consider before deploying LLM agents to production.

AWS 102

AWS Database Python Computer Science 102

Heartbeat

DECEMBER 15, 2023

And an Assessment of How They Impact Your ragas Metrics Photo by Ilya Pavlov on Unsplash If you’ve ever wondered how the quality of information sourced by language models affects their outputs, you’re in the right place. I’m trying to unpack how different document loaders in LangChain impact a Retrieval Augmented Generation (RAG) system.

Database 52

Database Natural Language Processing AI AI 52

AWS Machine Learning Blog

NOVEMBER 15, 2023

Llama 2 demonstrates the potential of large language models (LLMs) through its refined abilities and precisely tuned performance. Diving deeper into Llama 2’s architecture, Meta reveals that the model’s fine-tuning melds supervised fine-tuning (SFT) with reinforcement learning aided by human feedback (RLHF).

AWS 90

AWS Artificial Intelligence Artificial Intelligence AI 90

AWS Machine Learning Blog

APRIL 25, 2024

With enhanced understanding and more synthesized insights, organizations can make better informed strategic decisions, accelerate research, improve productivity, and increase their impact. Understanding the strengths and weaknesses of these techniques can help guide selection and improvement efforts.

AWS 108

AWS Algorithm Artificial Intelligence Artificial Intelligence 108

AWS Machine Learning Blog

NOVEMBER 22, 2023

Yes, the AWS re:Invent season is upon us and as always, the place to be is Las Vegas! You marked your calendars, you booked your hotel, and you even purchased the airfare. Now all you need is some guidance on generative AI and machine learning (ML) sessions to attend at this twelfth edition of re:Invent. And last but not least (and always fun!)

AWS 110

AWS ML ML AI 110

AWS Machine Learning Blog

OCTOBER 9, 2023

To demonstrate the easy customizability of the model, Mistral AI has also released a Mistral 7B Instruct model for chat use cases, fine-tuned using a variety of publicly available conversation datasets. With 7 billion parameters, Mistral 7B can be easily customized and quickly deployed.

AI 97

AI AI ML ML 97

Towards AI

OCTOBER 31, 2023

Last Updated on November 1, 2023 by Editorial Team Author(s): Towards AI Editorial Team Originally published on Towards AI. What happened this week in AI by Louie This week, President Joe Biden brought AI regulation back into the spotlight by signing an executive order to oversee artificial intelligence.

AI 93

AI AI Artificial Intelligence Artificial Intelligence 93