LLM Projects Workshop
We will be bringing together some of the founders and developers who are building in the LLM space!
This will be in our usual format of presentation (25 minute) followed by discussion (25 minute)
If you want to speak about any of these topics or similar ones, reach out to amir@ai.science
JOIN THE CONVERSATION ON OUR SLACK
JULY 7th (times are in ET):
09:00 Amir Hajian (VP, Data Science @ Arteria AI); LLM Starter Pack
10:00 Alaeddine Abdessalem (MLE @ Jina AI); ThinkGPT
11:00 Gabriele Venturi (Founder @ Sinaptik); Pandas AI
12:00 Amir Feizpour (PhD, CEO @ Aggregate Intellect); Building a Book that Writes Itself
13:00 Denys Linkov (ML Lead @ Voiceflow); LLM Personal Assistant
14:00 Suhas Pai (CTO @ Bedrock AI); Navigating LLM Landscape
15:00 Farshad Farahbakhshian (AI/ML Specialist @ Amazon); High Performance Computing on Cloud for Gen AI
16:00 Abi Aryan (Machine Learning Engineer @ Stealth); LLMs in Production
SPEAKERS
ABI ARYAN
Abi is a machine learning engineer with over 7 years of experience using ML research and adapting it to solve real-world engineering challenges working in machine learning infrastructure design and building production-level applications at scale. Before that, she was a visiting research scholar at UCLA working at the Cognitive Sciences Lab with Dr. Judea Pearl working on developing autonomous agents.
She is also currently writing a book titled LLMOps: Managing Large Language Models in Production for O'Reilly Publications and has authored an MLOps course. In her free time, she can be found tweeting at her Twitter handle - @goabiaryan
LLMs in Production - When deploying machine learning models in production, there are three properties that are commonly desired: generalization, evaluation, and cost-optimality. We conjecture that for machine learning models, it is impossible to optimize all three. I will talk about our framework for cost modeling and evaluation for large language models (LLMs) and present our LLMOps production pipeline.
ALAEDDINE ABDESSALEM
Alaeddine is a Machine Learning Engineer at Jina AI. At Jina AI, he contributes to open source projects like DocArray, a library for multimodal data and vector search and Jina, a framework for AI applications and services. He is also the author of ThinkGPT, a library for Chain of Thought techniques for LLMs.
ThinkGPT: Agent and Chain of Thought techniques for LLMs - ThinkGPT is a Python library designed to empower Large Language Models (LLMs) with advanced thinking and reasoning capabilities and to allow developers to create agents with LLMs. This talk will provide an overview of ThinkGPT's key features and how it addresses challenges such as limited context, one-shot reasoning, and decision-making. The library offers thinking building blocks like memory, self-refinement, knowledge compression, and natural language conditions. We will explore examples demonstrating ThinkGPT's applications, including teaching new languages to LLMs and enabling them to understand and generate code using new libraries. Additionally, we'll discuss the concept of generative agents and how they can be implemented with ThinkGPT. Join this talk to unlock the potential of ThinkGPT and leverage thinking abilities in your language models.
AMIR FEIZPOUR
Amir is the co-founder of Aggregate Intellect (https://ai.science/), a Smart Knowledge Navigator platform for R&D teams in emerging technologies like AI. Prior to this, Amir was an NLP Product Lead at Royal Bank of Canada, and held a postdoctoral position at University of Oxford conducting research on experimental quantum computing. Amir holds a PhD in Physics from University of Toronto.
Building a Live Book - In this talk we will present one of Aggregate Intellect community projects where we have been using Large Language Models to turn the transcripts of our community meetings into sections of an Open Book. We will also present a companion slack app that answers questions from this book and some other resources so that you don't have to read it.
DENYS LINKOV
Denys is the ML lead at Voiceflow focused on building the ML platform and data science offerings. His focus is on realtime NLP systems that help Voiceflow’s 60+ enterprise customers build better conversational assistants. Previously he worked at large bank as a senior cloud architect.
Diving into document question and answering systems with LLMs - We’ve seen the demos on how to answer questions from a document, but how does it work behind the scenes? In this talk we’ll focus on how embeddings and LLMs work for information retrieval tasks, and how to measure their effectiveness. We’ll also describe some the UX challenges when exposing these natural language retrieval systems to end users.
FARSHAD FARAHBAKHSHIAN
Farshad is an AI/ML Specialist at AWS and has helped model providers build their models on AWS and is now one of AWS' GenAI experts in helping Fortune 500 companies navigate the GenAI landscape.
Gen AI on Cloud - Farshad will be discussing how GenAI is pushing the limits of HPC ML Cloud environments and what many companies are asking for from model providers. This talk will touch the very bottom of the stack and then skip to the model layer of the stack.
GABRIELE VENTURI
Gabriele is a Software Engineer with over 10 years of experience in the field. He is also the founder of Sinaptik. With a mission to transform the way we interact with data, Gabriele strives to make data accessible to everyone, empowering individuals and organizations to make informed, data-driven decisions. Through his innovative approach, he seeks to break down barriers and democratize the world of data, enabling people from all backgrounds to harness its power and drive positive change.
PandasAI - Pandas AI is a Python library that integrates generative artificial intelligence capabilities into Pandas, making dataframes conversational. With PandasAI, you can easily perform complex queries and plot chart in natural language. In this talk, Gabriele, the main author of this library will present his journey and demo some of the use cases.
AMIR HAJIAN
Amir Hajian (aka Dr. Haj) is the head of data science at Arteria AI. He has been leading Arteria's efforts to make unstructured data understandable using multimodal foundation models, LLMs and the state of the art in MLOps. Amir was previously Director of Applied Research at Scribd and Director of AI Research at Thomson Reuters.
LLM Starter Pack: A Pragmatic Guide to Success with the Large Language Models - Large Language Models (LLMs) have taken the world by storm. There is no AI conversation today that won't lead to "what about LLMs?". These models are great tools for solving some problems but can they be used everywhere and for all problems? When should we use them and which real-world problems are best solved without them? How do I pick my LLM? What is the best check list to have to make sure our machine-learning-powered products will be successful in the age of LLMs?
We will address these questions by looking at a combination of scientific evidence, business requirements, financial realities and engineering facts.
SUHAS PAI
Suhas is the CTO & Co-founder of Bedrock AI, an NLP startup operating in the financial domain, where he conducts research on LLMs, domain adaptation, text ranking, and more. He was the co-chair of the Privacy WG at BigScience, the chair at TMLS 2022 and TMLS NLP 2022 conferences, and is currently writing a book on Large Language Models.
Which open-source LLM to choose for your task - Dozens of open-source LLMs have pounced on the scene in the last several months. Can you actually replace chat-gpt/gpt-4 with them? What are they useful for and how can you use them in production? How do you select one from dozens of available models? What are LLM evaluation measures actually measuring? In this talk, we will explore these questions and try to provide a framework to resolve the build vs buy conundrum that many individuals and organizations find themselves in
