simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
- Version
- 1.0.0
- License
- MIT
Pinned to revision df088027ff23, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/simpo-training/SKILL.md
- skills/simpo-training/references/datasets.md
- skills/simpo-training/references/hyperparameters.md
- skills/simpo-training/references/loss-functions.md
Every link opens the file at its source, pinned to the revision this page describes.