Creating a New Custom Model in Generative AI
Create a new custom model using a pretrained foundational model as a base. Provide your own dataset for the training.
- In the navigation bar of the Console, select a region with Generative AI, for example, US Midwest (Chicago). If you don't know which region to select, see Regions with Generative AI.
- Open the navigation menu and click Analytics & AI. Under AI Services, click Generative AI.
- In the left navigation, choose a compartment for the custom model.
- Click Custom models.
- Click Create model.
- Click Create a new model.
- Select a compartment to create the model in. The default compartment is the one you selected in step 3, but you can select any compartment that you have permission to work in.
- (Optional)
Enter a name for the custom model. Start the name with a letter or underscore, followed by letters, numbers, hyphens, or underscores. The length can be 1–255 characters. If you leave the name blank, the system generates a name that you can change later.
The generated name has the format
generativeaimodel<timestamp>
.For example:
generativeaimodel20240117184419
- (Optional)
Enter a version and description. If you leave the version blank, the system generates a version that you can change later.
The generated version has the format
v<timestamp>
.For example:
v20240117184419
- Click Next.
-
Choose a Base Model for the custom model.
For the base model details, see the text generation pretrained models.
-
Choose a Fine-tuning method.
-
Choose a fine-tuning dedicated AI cluster by performing one of the following actions:
- Click a Dedicated AI cluster from the drop-down list. If you just created a cluster, wait for that cluster to become active. Ensure that the base model that's associated with this cluster matches the base model in step 11.
- In the Dedicated AI cluster drop-down list, click Create new dedicated AI cluster and perform the following steps:
- (Optional) Enter a name and description.
- Choose a Base model that matches the base model in step 11.
- Read the commitment unit hours for the fine-tuning dedicated AI cluster and click to agree with the commitment.
- Click Create and wait for the cluster to become active.
- From the Dedicated AI cluster drop-down list, click the dedicated AI cluster that you created.
- (Optional) Click Show hyperparameters, review the hint text and tooltips and hint text and update the values. To reset, click Restore defaults.
- Click Next.
-
Click the name of the bucket that contains the training dataset. If the bucket is not listed:
- Ensure that the bucket is in the same region as the custom model.
- Click Change compartment and choose the compartment that hosts the bucket with the training data.
- Ask an administrator to give you permission to buckets and objects in this compartment.
- Click the name of the Training file.
- Preview how the data in the training file is ingested. If the data records parse correctly, click Submit. Otherwise, fix the data.