huggingface

huggingface/alignment-handbook

steady

Robust recipes to align language models with human and AI preferences

Python View on GitHub

Stars

5,629

Forks

492

Open issues

92

24h

+1

+0.0%

7d

+9

+0.2%

Refresh

2h

Star history (7 days)

Last checked

4m ago

Last pushed

26 May 2026

Next check

just now