Deploying LLMs on Structured Data Tasks: Lessons from the Trenches
Laurel Orr is a researcher at Numbers Station working applying generative AI to data tasks. She graduated with a PhD in Databases and Data Management from Paul G Allen School for Computer Science and Engineering at the University of Washington and then was a PostDoc at Stanford working for Chris Ré in the HazyReserach Labs. Her research interests are broadly at the intersection of artifical intelligence, foundation models, and data management. She focuses on how to train, customize, and deploy foundation models to data tasks such as data cleaning, record matching, and generating code snippets for determinisitic data transformations. This includes problems around data curation for training, efficient model training and inference for batch workloads, and prompting paradigms for high performant, personalized models.
Laurel Orr is a researcher at Numbers Station working applying generative AI to data tasks. She graduated with a PhD in Databases and Data Management from Paul G Allen School for Computer Science and Engineering at the University of Washington and then was a PostDoc at Stanford working for Chris Ré in the HazyReserach Labs. Her research interests are broadly at the intersection of artifical intelligence, foundation models, and data management. She focuses on how to train, customize, and deploy foundation models to data tasks such as data cleaning, record matching, and generating code snippets for determinisitic data transformations. This includes problems around data curation for training, efficient model training and inference for batch workloads, and prompting paradigms for high performant, personalized models.
I'm a tech entrepreneur and I spent the last decade founding companies that drive societal change.
I am now building Deep Matter, a startup still in stealth mode...
I was most recently building Telepath, the world's most developer-friendly machine learning platform. Throughout my previous projects, I had learned that building machine learning powered applications is hard - especially hard when you don't have a background in data science. I believe that this is choking innovation, especially in industries that can't support large data teams.
For example, I previously co-founded Call Time AI, where we used Artificial Intelligence to assemble and study the largest database of political contributions. The company powered progressive campaigns from school board to the Presidency. As of October, 2020, we helped Democrats raise tens of millions of dollars. In April of 2021, we sold Call Time to Political Data Inc.. Our success, in large part, is due to our ability to productionize machine learning.
I believe that knowledge is unbounded, and that everything that is not forbidden by laws of nature is achievable, given the right knowledge. This holds immense promise for the future of intelligence and therefore for the future of well-being. I believe that the process of mining knowledge should be done honestly and responsibly, and that wielding it should be done with care. I co-founded Telepath to give more tools to more people to access more knowledge.
I'm fascinated by the relationship between technology, science and history. I graduated from UC Berkeley with degrees in Astrophysics and Classics and have published several papers on those topics. I was previously a researcher at the Getty Villa where I wrote about Ancient Greek math and at the Weizmann Institute, where I researched supernovae.
I currently live in New York City. I enjoy advising startups, thinking about how they can make for an excellent vehicle for addressing the Israeli-Palestinian conflict, and hearing from random folks who stumble on my LinkedIn profile. Reach out, friend!
I'm a tech entrepreneur and I spent the last decade founding companies that drive societal change.
I am now building Deep Matter, a startup still in stealth mode...
I was most recently building Telepath, the world's most developer-friendly machine learning platform. Throughout my previous projects, I had learned that building machine learning powered applications is hard - especially hard when you don't have a background in data science. I believe that this is choking innovation, especially in industries that can't support large data teams.
For example, I previously co-founded Call Time AI, where we used Artificial Intelligence to assemble and study the largest database of political contributions. The company powered progressive campaigns from school board to the Presidency. As of October, 2020, we helped Democrats raise tens of millions of dollars. In April of 2021, we sold Call Time to Political Data Inc.. Our success, in large part, is due to our ability to productionize machine learning.
I believe that knowledge is unbounded, and that everything that is not forbidden by laws of nature is achievable, given the right knowledge. This holds immense promise for the future of intelligence and therefore for the future of well-being. I believe that the process of mining knowledge should be done honestly and responsibly, and that wielding it should be done with care. I co-founded Telepath to give more tools to more people to access more knowledge.
I'm fascinated by the relationship between technology, science and history. I graduated from UC Berkeley with degrees in Astrophysics and Classics and have published several papers on those topics. I was previously a researcher at the Getty Villa where I wrote about Ancient Greek math and at the Weizmann Institute, where I researched supernovae.
I currently live in New York City. I enjoy advising startups, thinking about how they can make for an excellent vehicle for addressing the Israeli-Palestinian conflict, and hearing from random folks who stumble on my LinkedIn profile. Reach out, friend!
Join us for an introduction to NSQL, a new family of open-source foundation models with up to 7B parameters automating SQL generation tasks. We will explore the limitations of existing open and closed-source foundation models for enterprise use, including issues of customization, quality, and privacy. We will highlight how NSQL addresses these challenges with its open-source nature, specialized training for SQL tasks, and a range of model sizes to accommodate diverse hardware configurations. Included in the talk will be NSQL's data generation process and GPU training approach, underlining its advantages over other foundation models for SQL generation. We will demonstrate how the NSQL models outperform existing open source models for SQL generation and, by starting from the newest LLama2 commercially available model, we even beat closed source models.