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.
no risky patterns detected
Type: Agent skill (SKILL.md) · Category: LLM & Model APIs · Source: https://github.com/dabit3/sonic-agent/tree/HEAD/optional-skills/mlops/simpo
| Capabilities (fewer powerful permissions = higher) | 50/50 |
| Maintenance | 26/35 |
| Documentation | 15/15 |
Always review files before installing. How scores work. Request a correction