Sveriges mest populära poddar
Super Data Science: ML & AI Podcast with Jon Krohn
VetenskapTeknologi

650: SparseGPT: Remove 100 Billion Parameters but Retain 100% Accuracy

8 min•3 februari 2023

SparseGPT is a noteworthy one-shot pruning technique that can halve the size of large language models like GPT-3 without adversely affecting accuracy. In this episode, Jon Krohn provides an overview of this development and explains its commercial and environmental implications.

Additional materials: www.superdatascience.com/650


Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.

Fler avsnitt av Super Data Science: ML & AI Podcast with Jon Krohn

Visa alla avsnitt av Super Data Science: ML & AI Podcast with Jon Krohn
983: AI in the Classroom: How a Top Elementary School Is Doing It Right, with Principal Traci Walker Griffith
•1 tim 13 min
982: In Case You Missed It in March 2026
•44 min
981: How Data Engineers Are “10x’ing” Themselves With Agents, feat. Matt Glickman
•1 tim 15 min
980: AI Making Theoretical Physics Breakthroughs
•10 min
979: Agentic Data Management and the Future of Enterprise AI, with Rohit Choudhary
•1 tim 5 min
978: A Post-Transformer Architecture Crushes Sudoku (Transformers Solve ~0%)
•11 min
977: Attention, World Models and the Future of AI, with Prof. Kyunghyun Cho
•1 tim 18 min
976: NVIDIA’s Nemotron 3 Super: The Perfect LLM for Multi-Agent Systems
•10 min
975: Unmetered Intelligence is Heralding the Next Renaissance, with Zack Kass
•1 tim 13 min
974: When Will The AI Bubble Burst? How Bad Will It Be?
•14 min

Super Data Science: ML & AI Podcast with Jon Krohn med Jon Krohn finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.