Rank Responses to Align Language Models with Human Feedback (RRHF): A new method to align LLMs from preferences. 🔎🤖 👉https://t.co/KqGsCG6zDg 🧵1/3 https://t.co/5jwodGGdNS
— Philipp Schmid (@_philschmid) Aug 13, 2023
from Twitter https://twitter.com/_philschmid
August 13, 2023 at 01:48AM
via IFTTT
No comments:
Post a Comment