skills.rest
microsoft
microsoftOFFICIAL
Explore all skills by this author →
Website𝕏@OpenAtMicrosoftGitHub

finetuning

Fine-tune AI models on Azure AI Foundry using SFT, DPO, or RFT.

2.9k|323|Updated Jan 16, 2026
Search Tags:#ai#azure#machine learning#training data#model fine-tuning
One-click install
npx skills add https://github.com/microsoft/skills --skill finetuning-microsoft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: finetuning
Source: https://github.com/microsoft/skills/tree/main/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning
Command: npx skills add https://github.com/microsoft/skills --skill finetuning-microsoft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires azure-identity, azure-ai-projects, openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to fine-tune AI models on Azure AI Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). It covers dataset preparation, training job submission, deployment, and evaluation.

Core Features & Use Cases

  • Model Fine-Tuning: Fine-tune models using SFT, DPO, or RFT, with options for dataset preparation, training, deployment, and evaluation.
  • Dataset Preparation: Prepare and validate training data, generate synthetic data, and ensure data quality.
  • Training & Deployment: Submit training jobs, monitor progress, deploy fine-tuned models, and evaluate their performance.
  • Use Case: Imagine you have a pre-trained language model that you want to fine-tune on a specific dataset for better performance in a specific domain, such as medical coding or legal analysis.

Quick Start

Use the finetuning skill to submit a supervised training job on your dataset 'dataset.jsonl'.

Frequently Asked Questions about finetuning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fine-tune an AI model using Azure AI Foundry?▼

You can fine-tune AI models on Azure AI Foundry by using this skill to prepare datasets, submit training jobs, deploy the customized models, and evaluate their performance across your specific domain.

What is the difference between SFT, DPO, and RFT for model fine-tuning?▼

SFT uses supervised learning for direct training, DPO uses preference data to align model behavior, and RFT applies reinforcement learning with graders. This skill supports all three methods on Azure AI Foundry.

Do I need the Azure SDKs or CLI tools to submit a training job?▼

Yes, submitting a training job requires access to Azure AI Foundry and associated SDKs or CLI tools. You also need dependencies like azure-identity, azure-ai-projects, and openai configured in your environment.

Can I generate synthetic data for model fine-tuning?▼

Yes, dataset preparation features allow you to prepare and validate training data, generate synthetic data, and ensure data quality before submitting your supervised or preference-based training jobs.

How do I evaluate fine-tuned model performance after deployment?▼

After deploying your fine-tuned models, you can use the evaluation features within this skill to assess their performance and ensure they meet the specific requirements of your target domain.

Related Skills

Explore More Software Engineering Skills→
anishi1222anishi1222

finetuning

Fine-tune AI models on Azure AI Foundry with supervised, preference, or reinforcement learning.

Community
Advanced
jorgeasaurusjorgeasaurus
12

finetuning

Fine-tune machine learning models on Azure AI Foundry with Python scripts.

Community
Advanced
davidrrowleydavidrrowley

azure-ai-projects-py

Manage Azure Foundry AI agents and project resources with the azure-ai-projects Python SDK.

Community
Advanced
SignmanalSignmanal
1

fine-tuning-with-trl

Generate TRL training pipelines for LLM post-training and RLHF workflows.

Community
Advanced