Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
安装
npx skills add NousResearch/hermes-agent --skill peftnpx skills add NousResearch/hermes-agent --skill peft -a claude-code -gnpx skills add NousResearch/hermes-agent --skill peft -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/peftgh skill install NousResearch/hermes-agent peftgit 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/peft ~/.claude/skills/peft # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/peft ~/.agents/skills/peft # Codex, Cursor, Gemini CLI, Copilot, OpenCode