gcloud beta ai model-garden models list-deployment-config

Stay organized with collections Save and categorize content based on your preferences.

gcloud beta ai model-garden models list-deployment-config - list the machine specifications supported by and verified for a model in Model Garden

gcloud beta ai model-garden models list-deployment-config --model=MODEL [--hugging-face-access-token=HUGGING_FACE_ACCESS_TOKEN] [--filter=EXPRESSION] [--sort-by=[FIELD,…]] [GCLOUD_WIDE_FLAG …]

gcloud ai model-garden models list-deployment-config --model=google/gemma2@gemma-2-9b

To list the supported machine specifications for a Hugging Face model meta-llama/Meta-Llama-3-8B, run:

gcloud ai model-garden models list-deployment-config --model=meta-llama/Meta-Llama-3-8B

--model=MODEL

The model to be deployed. If it is a Model Garden model, it should be in the format of {publisher_name}/{model_name}@{model_version_name}, e.g. google/gemma2@gemma-2-2b. If it is a Hugging Face model, it should be in the convention of Hugging Face models, e.g. meta-llama/Meta-Llama-3-8B.

--hugging-face-access-token=HUGGING_FACE_ACCESS_TOKEN

The access token from Hugging Face needed to read the model artifacts of gated models in order to generate the deployment configs. It is only needed when the Hugging Face model to deploy is gated and not verified by Model Garden. You can use the gcloud ai alpha/beta model-garden models list command to find out which ones are verified by Model Garden.

--filter=EXPRESSION

Apply a Boolean filter EXPRESSION to each resource item to be listed. If the expression evaluates True, then that item is listed. For more details and examples of filter expressions, run $ gcloud topic filters. This flag interacts with other flags that are applied in this order: --flatten, --sort-by, --filter, --limit.

--sort-by=[FIELD,…]

Comma-separated list of resource field key names to sort by. The default order is ascending. Prefix a field with ``~´´ for descending order on that field. This flag interacts with other flags that are applied in this order: --flatten, --sort-by, --filter, --limit.

Run $ gcloud help for details.