Super Data Science: ML & AI Podcast with Jon Krohn

695: NLP with Transformers, feat. Hugging Face's Lewis Tunstall

Jul 11, 2023
Guest
Lewis Tunstall
Lewis Tunstall, Hugging Face's ML Engineer, delves into transformers in NLP, encoder-decoder structures, Hugging Face's role, democratizing ML models, and the importance of understanding transformers' inner workings. They explore the evolution of transformers in NLP, limitations of decoder models, AI companionship, deploying ML models, GPT-4 development, Hugging Face ecosystem, and balancing secrecy vs transparency in AI development.
Ask episode
Chapters
Transcript
Episode notes
1
Intro
00:00 • 4min
2
The Evolution and Variants of Transformers in Natural Language Processing
04:01 • 13min
3
Exploring Transformers in NLP: Encoder-Decoder Structure and Model Evolution
16:52 • 5min
4
Decoder Models in NLP: Limitations and Advancements
21:43 • 9min
5
The Future of AI Companionship and Importance of NLP Understanding
30:29 • 2min
6
Understanding the Inner Workings of Transformers in NLP
32:15 • 10min
7
Discussion on Deploying Machine Learning Models and Exploring Open Source Alternatives
42:44 • 6min
8
Enhancing Efficiency and Security in GPT-4 Development
48:40 • 8min
9
Evolution of Hugging Face Ecosystem
56:32 • 32min
10
Balancing Secrecy vs Transparency in AI Development
01:28:46 • 9min