uclaml/SPPO

The official implementation of Self-Play Preference Optimization (SPPO)

Training & fine-tuningPython Apache-2.0 48created 2024-06-13

Stars

589

1-day growth

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

#deep-learning#fine-tuning#large-language-models#rlhf#self-play

Top contributors

Not collected yet (contributors job).

uclaml/SPPO · AI Repo Stats