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.
安装
npx skills add NousResearch/hermes-agent --skill simponpx skills add NousResearch/hermes-agent --skill simpo -a claude-code -gnpx skills add NousResearch/hermes-agent --skill simpo -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/simpogh skill install NousResearch/hermes-agent simpogit clone --depth 1 https://github.com/NousResearch/hermes-agent /tmp/NousResearch__hermes-agent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/simpo ~/.claude/skills/simpo # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/simpo ~/.agents/skills/simpo # Codex, Cursor, Gemini CLI, Copilot, OpenCode