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 davila7/claude-code-templates --skill simpo-trainingnpx skills add davila7/claude-code-templates --skill simpo-training -a claude-code -gnpx skills add davila7/claude-code-templates --skill simpo-training -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/post-training-simpogh skill install davila7/claude-code-templates simpo-traininggit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-simpo ~/.claude/skills/simpo-training # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-simpo ~/.agents/skills/simpo-training # Codex, Cursor, Gemini CLI, Copilot, OpenCode