Create a dedicated AI cluster resource in OCI
Generative AI to use for fine-tuning custom models.
Important Some OCI
Generative AI foundational pretrained models supported for the
dedicated serving mode are now deprecated and will retire no sooner than 6 months after the release of the 1
st replacement model. You can fine-tune and host a foundational pretrained model on a dedicated AI cluster (
dedicated serving mode) until that model is
retired. For dedicated serving mode retirement dates, see
Retiring the Models.
-
In the navigation bar of the Console, select a region with Generative AI, for example, US Midwest (Chicago) or UK South (London). See which models are offered in your region.
-
Open the navigation menu and click Analytics & AI. Under AI Services, click Generative AI.
-
Select a compartment that you have permission to work in.
-
Click Dedicated AI clusters.
-
Click Create dedicated AI cluster.
-
Select a compartment to create the dedicated AI cluster 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 and description for the cluster. If you don't enter a name, the
system generates one that you can change later.
The generated name has the format
generativeaidedicatedaicluster<timestamp>.
For example:
generativeaidedicatedaicluster20240601202357
-
For Cluster type, select
Fine-tuning.
-
For Base model, select the base model for the custom model that you want to fine-tune on this cluster:
meta.llama-3.1-70b-instruct - Provisions 2 Large Generic units.cohere.command-r-16k - Provisions 8 Small Cohere V2 units. meta.llama-3-70b-instruct - Provisions 2 Large Generic units. (This model is deprecated.)
Important
The number of units in a fine-tuning cluster is preset and depends on the base model selected for fine-tuning. Fine-tuning clusters need more resources than hosting clusters because they use more GPUs. You can fine-tune several models on the same cluster, as long as the custom models train on the same base model.
-
Read the commitment unit hours for the fine-tuning cluster and select
the checkbox to agree to the commitment.
- (Optional)
Click Show advanced options and assign tags to this dedicated AI cluster.
-
Click Create.
Note
Fine-tuning clusters take some time to create. After a fine-tuning cluster is in an active state, you can use it to fine-tune custom models. You can select a cluster for fine-tuning when you create a custom model.