Cloudera Docs

Using Fine Tuning Studio

Fine-tuning is a process that involves training a specific model to meet the standards of an organization. By using fine-tuned models, you can improve the accuracy and performance of your LLMs, reduce training time, and achieve cost benefits. Fine-Tuning Studio simplifies this process by providing a comprehensive platform for organizing data, testing prompts, training adapters, and evaluating performance.

  1. In the Cloudera console, click the Cloudera AI tile.

    The Cloudera AI Workbenches page displays.

  2. Click on the name of the workbench.

    The workbenches Home page displays.

  3. Click Projects, and then click New Project to create a new project.

    In the left navigation pane, the new AI Studios option is displayed.

  4. Click AI Studios and select Fine Tuning Studio.

    The Fine Tuning Studio page is displayed.

  5. Select Resources in the top navigation bar for Fine Tuning Studio and click Import Base Models.

    The Import Base Models page is displayed.

  6. On the Fine Tuning Studio main page, select Resources in the top navigation bar, and click Import Datasets.

    The Import Datasets page is displayed.

  7. Select Resources in the top navigation bar for Fine Tuning Studio and click Create Prompts in the top navigation pane.

    The Create prompts page is displayed.

  8. Select Experiments in the top navigation bar for Fine Tuning Studio and click Train a New Adapter.
  9. Fill in the required fields of the Train a New Adapter page with the help of the instructions provided on the page.
  10. Click Start Job.
  11. Select Experiments in the top navigation bar for Fine Tuning Studio and click Monitor Training Jobs.
  12. Select Experiments in the top navigation bar for Fine Tuning Studio and click Run MLFlow Evaluation.
  13. Select Experiments in the top navigation bar for Fine Tuning Studio and click View MLFlow Runs.
  14. If you want to export the Fine Tuning model, go to AI Workbench in the top navigation bar for Fine Tuning Studio and click Export And Deploy Model.

    You can select exporting the Fine Tuning Model to Cloudera AI Registry or to Cloudera AI Deployment. Models exported to Cloudera AI Registry can be found under Experiments in the left navigation pane, whereas models exported to Cloudera AI Model Deployment can be found under Model Deployments in the left navigation pane.

  15. For an example, select Examples in the top navigation pane.
  16. Export or import your metadata with the help of the Database Import Export button in the top navigation pane.