Published Feb 3, 2023
650: SparseGPT: Remove 100 Billion Parameters but Retain 100% Accuracy — with Jon Krohn
Explore SparseGPT, a revolutionary pruning technique that halves the size of large language models like GPT-3 while maintaining full accuracy, offering groundbreaking advancements in computational efficiency, cost reduction, and environmental sustainability. Jon Krohn discusses its transformative implications for both commercial applications and the future of AI modeling.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions666: GPT-4 — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions660: Five Ways to Use ChatGPT for Data Science — with Jon Krohn (@JonKrohnLearns)
Answers 383 questionsSDS 568: PaLM: Google's Breakthrough Natural Language Model — with Jon Krohn
Answers 383 questions
826: In Case You Missed It in September 2024 — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions676: The Chinchilla Scaling Laws — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions820: OpenAI's o1 "Strawberry" Models — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions