-You complete the fine-tuning of a generative model in Microsoft Foundry.

Correct sequence:

Create a Developer Tier deployment.

Evaluate and validate the model.

Create a Global Standard deployment.

The fine-tuned model should first be deployed using the Developer Tier because Microsoft specifically positions this deployment type for fine-tuned model candidate evaluation rather than production use . Developer Tier deployments provide a cost-efficient environment for testing custom models and do not provide a production SLA.

After deployment, the model should be evaluated and validated . Microsoft Foundry supports running the model through the playground and the Evaluations service to assess the deployed candidate against expected quality, safety, and task-performance criteria. Microsoft explicitly documents that evaluations can be executed against a deployed fine-tuned model candidate and compared with other model versions.

Only after the candidate satisfies the required validation criteria should it be promoted to a Global Standard deployment for production inference. Global Standard is designed for general production workloads and provides substantially more appropriate production characteristics than Developer Tier.

Register the fine-tuned model version is the distractor here. The scenario already states that fine-tuning is complete and the resulting model variant exists in Microsoft Foundry; the required promotion workflow is therefore test deployment → validation → production deployment .

Study Guide Reference: Implement machine learning model lifecycle and operations — fine-tuned model evaluation, controlled promotion, Developer Tier deployments, production deployment, and model lifecycle governance.