Deploying tuned models
You can tune a model to adapt it to a specific task, dataset, or use case . The tuning process adjusts the parameters or weights of a pre-trained model and improves the model's performance and accuracy. Deploy a tuned model so you can add it to a business workflow and start using foundation models in a meaningful way.
You can deploy a foundation model that is tuned with any of the following techniques:
- Low-rank adaptation (LoRA) fine tuning
- Quantized low-rank adaptation (QLoRA) fine tuning
Ways to work
You use various methods to deploy tuned foundation including:
- The Projects UI to deploy tuned models that are stored as tuning experiment assets in your project or Tuning Studio. For details, see Deploying tuned models from the UI.
- Programmatic methods to deploy tuned model assets. For details, see Deploying tuned models with code.
Requirements
Before you deploy a tuned model, you must complete the following tasks:
-
Tune a foundation model with the Tuning Studio or programmatically. For details, see Tuning foundation models.
-
For LoRA or QLoRA fine-tuned models only: Review the requirements for deploying models tuned with LoRA or QLoRA, including supported models, hardware and software requirements, and deployment types. For details, see Requirements for deploying LoRA or QLoRA tuned models.
Workflow
Whichever way you choose to work, the high-level workflow for deploying a tuned foundation model remains the same. Deploying a tuned model involves the following tasks:
- Optional: Create repository asset for the tuned foundation model, if the asset was not automatically created when you tuned the model.
- Deploy the tuned model asset.
- Inference the tuned model deployment to test the tuned foundation model's responses to textual inputs.
- Retrieve the endpoint URL for the tuned model deployment that you can use to access the deployment from your applications. From the Deployments tab of your project or deployment space, click the deployment name. In the API reference tab, find the private and public endpoint links and code snippets that you can use to include the endpoint details in an application.
Learn more
- You can manage your tuned model deployment in the same way as a custom foundation model deployment. For details, see Managing a custom foundation model deployment.
- Security and privacy for foundation models