Fine-tuning and Preference Alignment in a Single Streamlined Process

13/06/2024 35 min
Fine-tuning and Preference Alignment in a Single Streamlined Process

Listen "Fine-tuning and Preference Alignment in a Single Streamlined Process"

Episode Synopsis

Jiwoo Hong and  Noah Lee of KAIST AI are co-authors of ORPO: Monolithic Preference Optimization without Reference Model. Subscribe to the Gradient Flow Newsletter:  https://gradientflow.substack.com/Subscribe: Apple • Spotify • Overcast • Pocket Casts • AntennaPod • Podcast Addict • Amazon •  RSS.Detailed show notes can be found on The Data Exchange web site.