https://github.com/DaehanKim/EasyRLHF

EasyRLHF aims to provide an easy and minimal interface to train aligned language models, using off-the-shelf solutions and datasets
https://github.com/DaehanKim/EasyRLHF

dpo instruction-tuning ipo language-model rlhf rrhf sft

Last synced: about 2 months ago
JSON representation

EasyRLHF aims to provide an easy and minimal interface to train aligned language models, using off-the-shelf solutions and datasets

• Host: GitHub
• URL: https://github.com/DaehanKim/EasyRLHF
• Owner: DaehanKim
• Created: 2023-03-06T16:01:56.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-12T08:02:10.000Z (10 months ago)
• Last Synced: 2024-07-05T14:29:32.572Z (3 months ago)
• Topics: dpo, instruction-tuning, ipo, language-model, rlhf, rrhf, sft
• Language: Python
• Homepage:
• Size: 73.9 MB
• Stars: 6
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-human-in-the-loop - Github - DaehanKim/EasyRLHF - the-shelf solutions and datasets (Awesome RHLF / Tools and Resources)