Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model.
安装
npx skills add microsoft/GitHub-Copilot-for-Azure --skill finetuningnpx skills add microsoft/GitHub-Copilot-for-Azure --skill finetuning -a claude-code -gnpx skills add microsoft/GitHub-Copilot-for-Azure --skill finetuning -a codex -ggemini skills install https://github.com/microsoft/GitHub-Copilot-for-Azure.git --path plugins/azure-skills/skills/microsoft-foundry/finetuninggh skill install microsoft/GitHub-Copilot-for-Azure finetuninggit clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure /tmp/microsoft__GitHub-Copilot-for-Azure
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__GitHub-Copilot-for-Azure/plugins/azure-skills/skills/microsoft-foundry/finetuning ~/.claude/skills/finetuning # Claude Code
cp -R /tmp/microsoft__GitHub-Copilot-for-Azure/plugins/azure-skills/skills/microsoft-foundry/finetuning ~/.agents/skills/finetuning # Codex, Cursor, Gemini CLI, Copilot, OpenCode