I’m trying to follow this quickstart to deploy a model on vertex AI:

https://cloud.google.com/vertex-ai/docs/general/deployment

& I’m at the step where I’m supposed to run:

gcloud ai endpoints deploy-model ENDPOINT_ID
  --region=LOCATION_ID 
  --model=MODEL_ID 
  --display-name=DEPLOYED_MODEL_NAME 
  --min-replica-count=MIN_REPLICA_COUNT 
  --max-replica-count=MAX_REPLICA_COUNT 
  --traffic-split=0=100

How do I get a model id for a public model, ie one I found in Model Garden?

I tried out Llama 2 from its card page:
https://pantheon.corp.google.com/vertex-ai/publishers/meta/model-garden/llama2

& used its model id: publishers/meta/models/llama2

However then I get error:

ERROR: (gcloud.ai.endpoints.deploy-model) There is an error while getting the model information. Please make sure the model 'projects/my-test-project/locations/us-east1/models/publishers/meta/models/llama2' exists.

The error looks like it’s trying to read from my project / model registry rather than the public one. Can I force it to read from the public Model Garden one? Or do I need to do some setup like downloading the model to my private Model Registry?