@orchestra-research/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.

View in AI SkillSafe app
Scanned · no findings
0 downloads
0 stars
0 demos
SKILL.md

Embed badges

Add these to your README to show the skill's verification status.

SkillSafe verified badge
Verified badge
[![SkillSafe verified badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/simpo-training/verified)](https://skillsafe.ai/skill/@orchestra-research/simpo-training/)
Installs badge
Installs badge
[![Installs badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/simpo-training/installs)](https://skillsafe.ai/skill/@orchestra-research/simpo-training/)
Scan badge
Scan badge
[![Scan badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/simpo-training/scan)](https://skillsafe.ai/skill/@orchestra-research/simpo-training/)
Eval pass rate badge
Eval pass rate
[![Eval pass rate badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/simpo-training/eval)](https://skillsafe.ai/skill/@orchestra-research/simpo-training/)