Published On Jun 3, 2024
Today, we're joined by Sasha Luccioni, AI and Climate lead at Hugging Face, to discuss the environmental impact of AI models. We dig into her recent research into the relative energy consumption of general purpose pre-trained models vs. task-specific, non-generative models for common AI tasks. We discuss the implications of the significant difference in efficiency and power consumption between the two types of models. Finally, we explore the complexities of energy efficiency and performance benchmarking, and talk through Sasha’s recent initiative, Energy Star Ratings for AI Models - https://huggingface.co/blog/sasha/ene..., a rating system designed to help AI users select and deploy models based on their energy efficiency.
The complete show notes for this episode can be found at http://twimlai.com/go/687.
🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi...
🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/
Follow us on Twitter: / twimlai
Follow us on LinkedIn: / twimlai
Join our Slack Community: https://twimlai.com/community/
Subscribe to our newsletter: https://twimlai.com/newsletter/
Want to get in touch? Send us a message: https://twimlai.com/contact/
📖 CHAPTERS
===============================
00:00 - Introduction
1:47 - Career background
4:19 - Energy consumption of LLMs
7:49 - Power Hungry Processing: Watts Driving the Cost of AI Deployment? paper
12:35 - Trends toward smaller models
14:10 - Climate impacts and concentration of power of large models
20:10 - Task-specific vs. general-purpose models
22:20 - Challenges in current AI research
27:37 - Energy Star Ratings for AI Models
34:39 - Energy efficiency and performance benchmarking challenges
42:32 - Challenges in comparing fine-tuned and generative models
43:57 - Future directions for Energy Star Ratings for AI Models
45:20 - Insights on model cards
🔗 LINKS & RESOURCES
===============================
Energy Star Ratings for AI Models - https://huggingface.co/blog/sasha/ene...
Power Hungry Processing: Watts Driving the Cost of AI Deployment? - https://arxiv.org/abs/2311.16863
Mind your Language (Model): Fact-Checking LLMs and their Role in NLP Research and Practice - https://arxiv.org/abs/2308.07120
Measuring Data - https://arxiv.org/abs/2212.05129
📸 Camera: https://amzn.to/3TQ3zsg
🎙️Microphone: https://amzn.to/3t5zXeV
🚦Lights: https://amzn.to/3TQlX49
🎛️ Audio Interface: https://amzn.to/3TVFAIq
🎚️ Stream Deck: https://amzn.to/3zzm7F5