Firectl
Update Resources
Firectl
Update Resources
Updates Resources on Fireworks AI platform
firectl update model [flags]
Example
firectl update model my-model --display-name="New Name"
Flags
--context-length int32 The maximum context length of the model.
--default-draft-model string The default speculative draft model to use when creating a deployment.
--default-draft-token-count int32 The default speculative draft token count when creating a deployment.
--description string The description of the model.
--display-name string The display name of the model.
--github-url string The GitHub URL of the model.
-h, --help help for model
--hugging-face-url string The Hugging Face URL of the model.
--public Whether the model is publicly accessible.
--supports-image-input Whether the model supports image inputs.
--supports-tools Whether the model supports function calling.
Update a user
firectl update user <fireworks-account-id> [flags]
Example
firectl update user my-user --display-name="Alice Cullen"
Flags
--display-name string The display name of the user.
-h, --help help for user
--user string The role of the user. Must be one of {user, admin}.
Update a deployment
firectl update deployment <deployment-name> [flags]
Example
firectl update deployment my-deployment
Flags
--description string Description of the deployment. Must be fewer than 1000 characters long.
--display-name string Human-readable name of the deployment. Must be fewer than 64 characters long.
-h, --help help for deployment
--max-peft-batch-size int32 Max batching of concurrent PEFT requests to the server.
--max-replica-count int32 The maximum number of replicas.
--min-replica-count int32 The minimum number of replicas. (default 1)
--scale-down-window duration The duration the autoscaler will wait before scaling down a deployment after observing decreased load. Default is 10m.
--scale-to-zero-window duration The duration after which there are no requests that the deployment will be scaled down to zero replicas, if min-replica-count is 0. Default 1h.
--scale-up-window duration The duration the autoscaler will wait before scaling up a deployment after observing increased load. Default is 30s.
--unused-auto-delete-duration duration The duration for which if no requests are received, the deployment will automatically be deleted. If 0, the auto-deletion is disabled.
--world-size int32 The number of GPUs the base model is served with.
Update a dataset
firectl update dataset [flags]
Example
firectl update dataset my-dataset
Flags
--display-name string The display name of the model.
-h, --help help for dataset
Was this page helpful?