Fine-Tuning the Base Models in Generative AI
Create custom models in OCI Generative AI by fine-tuning the base models with your own dataset. You can create new custom models or create new versions of existing custom models.
The following workflow displays the tasks for fine-tuning a pretrained model and hosting the fine-tuned model.
The following tasks provide the steps for fine-tuning a pretrained model and hosting the fine-tuned model:
- Create the training dataset.
- Add the dataset to an Object Storage bucket.
- Create a fine-tuning dedicated AI cluster.
- Create a new custom model or create a new version from an existing model on the fine-tuning dedicated AI cluster.
- Create a hosting dedicated AI cluster.
- Create an endpoint for the custom model on the hosting dedicated AI cluster.
- Run the custom model in the playground.
Managing Custom Models
In OCI Generative AI, you create custom models by fine-tuning the base models with your own datasets. You can create custom models or create new versions of existing custom models.
After you create a custom model or create a new version from an existing model, you can perform the following tasks on the custom models: