microsoft-foundrymicrosoft-foundryOfficialยท1 Agent Skills Included

fine-tuning

End-to-end model fine-tuning on Azure AI Foundry

Guides the full fine-tuning lifecycle on Azure AI Foundry, from dataset creation and validation to training, evaluation, and deployment. Covers SFT, DPO, and RFT techniques with ready-made scripts, sample datasets, and step-by-step workflows. Eliminates guesswork around data formats, grader design, hyperparameters, and platform errors so teams ship better models faster.
npx skills add microsoft-foundry/fine-tuning --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install fine-tuning?โ–ผ

Run `npx skills add microsoft-foundry/fine-tuning --all -g -y` in your terminal to install all skills in this repository globally.

How to fine-tune a model on Azure AI Foundry?โ–ผ

Open the repository in your coding agent and describe your task. The skill walks you through dataset preparation, job submission, monitoring, evaluation, and deployment step by step.

What fine-tuning techniques are supported?โ–ผ

The skill covers Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Reinforcement Fine-Tuning (RFT), plus distillation and synthetic data generation.

Does it work with Copilot, Claude Code, and Codex?โ–ผ

Yes. The skill auto-discovers in GitHub Copilot, Claude Code, and Codex through dedicated skill folders, so no manual setup is needed.

Do I need fine-tuning experience to use it?โ–ผ

No. Guided workflows like quickstart and full-pipeline explain each stage in plain steps, and scripts handle validation, submission, and deployment for you.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’