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 Orchestra-Research/AI-Research-SKILLs --skill peft-fine-tuningnpx skills add Orchestra-Research/AI-Research-SKILLs --skill peft-fine-tuning -a claude-code -gnpx skills add Orchestra-Research/AI-Research-SKILLs --skill peft-fine-tuning -a codex -ggemini skills install https://github.com/Orchestra-Research/AI-Research-SKILLs.git --path 03-fine-tuning/peftgh skill install Orchestra-Research/AI-Research-SKILLs peft-fine-tuninggit clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs /tmp/Orchestra-Research__AI-Research-SKILLs
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/03-fine-tuning/peft ~/.claude/skills/peft-fine-tuning # Claude Code
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/03-fine-tuning/peft ~/.agents/skills/peft-fine-tuning # Codex, Cursor, Gemini CLI, Copilot, OpenCode