Oracle Cloud Infrastructure Documentation
Try Free Tier

Listing the Dedicated AI Clusters in Generative AI

View all of the dedicated AI clusters in a compartment in OCI Generative AI.

  1. 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.
  2. Open the navigation menu  and select Analytics & AI. Under AI Services, select Generative AI.
  3. In the left navigation, select the compartment that contains the dedicated AI clusters.
  4. Click Dedicated AI clusters.
  5. For each listed dedicated AI cluster, view the following properties:
    • Dedicated AI cluster name
    • State
      • Creating
      • Active
      • Updating
      • Deleting
      • Deleted
      • Failed
    • Creation date and time
    • Type
      • Fine-tuning
      • Hosting
    • Remaining endpoint capacity
      • Applies only to hosting clusters.
      • With a capacity of 50 units, calculates how many units are available to add to the cluster.
      • You can add one endpoint to each unit.
    • Unit size for fine-tuning clusters
      • Large Generic, for the base models meta.llama-3-70b-instruct and meta.llama-3.1-70b-instruct
      • Small Cohere, if the base model is cohere.command-light
      • Small Cohere V2, for the base models cohere.command-r-16k and cohere.command-r-08-2024
      • Large Cohere, if the base model is cohere.command
    • Unit size for hosting clusters
      • Small Generic V2, if the base model is meta.llama-3.2-11b-vision-instruct
      • Large Generic, for the base models meta.llama-3.1-70b-instruct and meta.llama-3-70b-instruct
      • Large Generic V2, if the base model is meta.llama-3.2-90b-vision-instruct
      • Large Generic 4, if the base model is meta.llama-3.1-405b-instruct
      • Llama2 70, if the base model is meta.llama-2-70b-chat
      • Small Cohere, if the base model is cohere.command-light
      • Small Cohere V2, for the base models, cohere.command-r-16k and cohere.command-r-08-2024
      • Large Cohere, if the base model is cohere.command
      • Large Cohere V2_2, for the base models cohere.command-r-plus and cohere.command-r-plus-08-2024
      • Embed Cohere, for the base models cohere.embed.english-light-v3.0, cohere.embed.english-v3.0, cohere.embed.multilingual-light-v3.0, and cohere.embed.multilingual-v3.0
    • Number of units
      • 8 for fine-tuning clusters with the base model of cohere.command-r-16k and cohere.command-r-08-2024 and 2 for other available fine-tuning models
      • 1 or more for hosting clusters
    • Created by
    • Description

Was this article helpful?