https://github.com/xrsrke/instructGOOSE

Implementation of Reinforcement Learning from Human Feedback (RLHF)
https://github.com/xrsrke/instructGOOSE

chatgpt human-feedback instructgpt reinforcement-learning rlhf

Last synced: about 1 month ago
JSON representation

Implementation of Reinforcement Learning from Human Feedback (RLHF)

• Host: GitHub
• URL: https://github.com/xrsrke/instructGOOSE
• Owner: xrsrke
• License: mit
• Created: 2022-12-28T06:39:51.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-04-07T08:45:59.000Z (over 1 year ago)
• Last Synced: 2024-04-26T02:22:29.546Z (5 months ago)
• Topics: chatgpt, human-feedback, instructgpt, reinforcement-learning, rlhf
• Language: Jupyter Notebook
• Homepage: https://xrsrke.github.io/instructGOOSE/
• Size: 3.31 MB
• Stars: 163
• Watchers: 4
• Forks: 20
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-human-in-the-loop - Github - xrsrke/instructGOOSE
• Awesome-Prompt-Engineering - [Github