Fine-Tuning LLMs, Hugging Face & Open Source with Lewis Tunstall #49 Artwork

AI Stories

Artificial Intelligence, Machine Learning, Data Science and Deep Learning are completely changing the world we live in today. Companies around the world start to make sensible use of big data to influence business decisions and create our future. From video recommendations to autonomous driving, from stock prediction to weather forecasting, the AI revolution is everywhere. The AI stories podcast brings together some of the best Data Scientists, Machine Learning Engineers, Business leaders and researchers that are at the front of this revolution. They are here to talk about their career, how they arrive where they are, give advice and share their vision. They explain how they make use of AI in their daily routine, how they use algorithms to solve business problems and make the world a better place. They are here to share their stories: their AI stories. Hosted by Neil Leiser, Data Scientist at Iwoca. Follow Neil to learn more about career, Data Science, AI and Machine Learning. Linkedin: https://www.linkedin.com/in/leiserneil/ Twitter: https://twitter.com/LeiserNeil

All Episodes

AI Stories

Fine-Tuning LLMs, Hugging Face & Open Source with Lewis Tunstall #49

June 20, 2024 • Neil Leiser • Season 3 • Episode 15

Our guest today is Lewis Tunstall, LLM Engineer and researcher at Hugging Face and book author of "Natural Language Processing with Transformers".

In our conversation, we dive into topological machine learning and talk about giotto-tda, a high performance topological ml Python library that Lewis worked on. We then dive into LLMs and Transformers. We discuss the pros and cons of open source vs closed source LLMs and explain the differences between encoder and decoder transformer architectures. Lewis finally explains his day-to-day at Hugging Face and his current work on fine-tuning LLMs.

If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel.

Link to Train in Data courses (use the code AISTORIES to get a 10% discount): https://www.trainindata.com/courses?affcode=1218302_5n7kraba

Natural Language Processing with Transformers book: https://www.oreilly.com/library/view/natural-language-processing/9781098136789/

Giotto-tda library: https://github.com/giotto-ai/giotto-tda

KTO alignment paper: https://arxiv.org/abs/2402.01306

Follow Lewis on LinkedIn: https://www.linkedin.com/in/lewis-tunstall/

Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/

---

(00:00) - Intro

(03:00) - How Lewis Got into AI

(05:33) - From Kaggle Competitions to Data Science Job

(11:09) - Get an actual Data Science Job!

(15:18) - Deep Learning or Excel?

(19:14) - Topological Machine Learning

(28:44) - Open Source VS Closed Source LLMs

(41:44) - Writing a Book on Transformers

(52:33) - Comparing BERT, Early Transformers, and GPT-4

(54:48) - Encoder and Decoder Architectures

(59:48) - Day-To-Day Work at Hugging Face

(01:09:06) - DPO and KTO

(01:12:58) - Stories and Career Advice