Explore the cutting-edge techniques behind successful machine learning models like ChatGPT in this concise conference talk. Delve into Reinforcement Learning from Human Feedback (RLHF) and discover efficient training methods such as Parameter-Efficient Fine-Tuning (PEFT). Learn about on-device machine learning and various optimizations to enhance ML model performance. Led by Omar Sanseviero, a lead machine learning engineer at Hugging Face, this presentation offers valuable insights into modern ML practices in production environments. Gain knowledge from Sanseviero's extensive experience working on diverse ML projects, including ML for Art, Developer Advocacy Engineering, ML Partnerships, Mobile ML, and ML for Healthcare.
End-to-end Modern Machine Learning in Production - Part 2
Overview
Syllabus
End-to-end Modern Machine Learning in Production // Omar Sanseviero // LLMs in Prod Con Part 2
Taught by
MLOps.community
