AI Developers Release Open-Source Implementations of ChatGPT Training Algorithm, 24.01.2023
zuletzt bearbeitet: Sun, 26 Mar 2023 11:24:46 +0200
AI research groups LAION and CarperAI have released OpenAssistant and trlX, open-source implementations of reinforcement learning from human feedback (RLHF), the algorithm used to train ChatGPT. Independent AI developer Phil Wang has also open-sourced his own implementation of the algorithm.
https://www.infoq.com/news/2023/01/open-source-chatgpt/#
ChatGPT #
ChatGPTDiary #
CarperAI #
LAION #
OpenAssistant #
trIX #
PhilWang #
RLHF #
HumanFeedback #
ReinforcementLearning