https://github.com/EleutherAI/alignment-handbook

Robust recipes for to align language models with human and AI preferences
https://github.com/EleutherAI/alignment-handbook

Last synced: 3 months ago
JSON representation

Robust recipes for to align language models with human and AI preferences

• Host: GitHub
• URL: https://github.com/EleutherAI/alignment-handbook
• Owner: EleutherAI
• License: apache-2.0
• Fork: true (huggingface/alignment-handbook)
• Created: 2024-01-15T15:53:49.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-01-22T15:16:19.000Z (over 2 years ago)
• Last Synced: 2024-04-28T04:28:25.310Z (about 2 years ago)
• Homepage: https://huggingface.co/HuggingFaceH4
• Size: 128 KB
• Stars: 3
• Watchers: 2
• Forks: 1
• Open Issues: 0

Awesome Lists containing this project

• awesome-ai-ml-testing - Alignment Evaluation - Tools for testing goal alignment in agent-based AI systems. (🛡️ AI Safety Testing)