Admin

co admin

Admin operations

Options

  -h, --help   help for admin

co admin baselines

Baseline management

Options

  -h, --help   help for baselines

co admin baselines get

get baseline state from ID

co admin baselines get [flags]

Options

  -h, --help            help for get
      --id string       id of finetune
      --models          get information about models deployed in this state only
      --output string   output path, default stdout (default "-")

co admin baselines list

list baseline states

co admin baselines list [flags]

Options

      --after string     retrieve states that were set after this date in dd/mm/yyyy format
      --before string    retrieve states that were set before this date in dd/mm/yyyy format
      --email string     email of deployer
  -h, --help             help for list
      --id string        id of finetune
      --models           get information about models deployed in this state only
      --num-states int   number of states to return (default 10)
      --order string     ordering by deployed time (default "desc")
      --output string    output path, default stdout (default "-")
      --show-id          get id of baseline states

co admin baselines update

update baseline state

co admin baselines update [flags]

Options

      --force            force deployment
  -h, --help             help for update
      --state string     path to state file, or read from stdin by specifying "-"
      --vx-yaml string   path to vx yaml, or read from stdin by specifying "-"

co admin limits

Options

  -h, --help   help for limits

co admin limits list

list limits that an organization has

co admin limits list [organization_id] [flags]

Options

      --active   view only active limits
  -h, --help     help for list

co admin limits reset

reset an organization's usage and reset dates

co admin limits reset [organization_id] [flags]

Options

  -h, --help   help for reset

co admin limits set-active

make an existing limit active or not

co admin limits set-active [flags]

Options

      --active            active or not (default true)
      --endpoint string   endpoint name
  -h, --help              help for set-active
      --model string      model name
      --org-id string     organization id

co admin limits set-limit

set a limit to an organization's usage (endpoint level) and make it active

co admin limits set-limit [flags]

Options

      --endpoint string   endpoint name
  -h, --help              help for set-limit
      --limit int         character limit
      --model string      model name
      --org-id string     organization id

co admin organization

Options

  -h, --help   help for organization

co admin organization apply-finetune-policy

apply a finetune policy for an organization

co admin organization apply-finetune-policy [flags]

Options

  -h, --help                help for apply-finetune-policy
      --max-finetunes int   maximum finetunes allowed (default 15)
      --org-id string       ID of organization to apply policy to
      --tier string         finetune access tier, must be default or premium (default "default")

co admin organization create

create an organization

co admin organization create [name] [flags]

Options

  -h, --help                     help for create
      --onboarding-slug string   onboarding slug (default "strict-terms-and-privacy")
      --payment-type string      payment type, must be stripe or invoice (default "stripe")

co admin organization disable

disable an organization

co admin organization disable [org_name] [flags]

Options

  -h, --help   help for disable

co admin organization enable-subscription

enable an organization's subscriptions

co admin organization enable-subscription [flags]

Options

  -h, --help            help for enable-subscription
      --org-id string   org id to update

co admin organization list

list all organizations

co admin organization list [flags]

Options

  -h, --help            help for list
      --output string   output path, default stdout (default "-")

co admin organization set_payment_type

set an organization's payment type

co admin organization set_payment_type [flags]

Options

  -h, --help            help for set_payment_type
      --org-id string   org id to update
      --type string     specify payment type to set for org, must be stripe or invoice

co admin private-model

Upload and manage private models

Options

  -h, --help   help for private-model

co admin private-model create

Create a new private model.

co admin private-model create [name] [flags]

Options

      --bert-batching-parameters-file string   path to BERT batching parameters file
      --bert-path string                       path to BERT model
      --cpu string                             Amount of cpu to allot to model (default "2")
      --encoder-dir string                     Path to encoder (default "gs://cohere-prod/encoders/coheretext50k-30Mplus1")
      --gpt-batching-parameters-file string    path to GPT batching parameters file
      --gpt-path string                        path to GPT model
      --gpu string                             Amount of gpu to allot to model (default "0")
  -h, --help                                   help for create
      --max int32                              maximum replicas (default 10)
      --max-bert-tokens int                    maximum token length for BERT model (default 1024)
      --max-gpt-tokens int                     maximum token length for GPT model (default 1024)
      --mem string                             Amount of memory to allot to model (default "4G")
      --min int32                              minimum replicas (default 1)
      --model-size string                      path to GPT model
      --org-id string                          organization that can use this private model, we'll grant them access after creating it
      --replicas int                           how many replicas to create (don't use if autoscaling)
      --route string                           route to access to model from (i.e. api.cohere.ai/{route})
      --target-gpu string                      target gpu utilization (%), set to 0 to not scale based off this (default "65")

co admin private-model delete

Delete a private model.

co admin private-model delete [id] [flags]

Options

  -h, --help   help for delete

co admin private-model grant-access

Grant an org access to a private model.

co admin private-model grant-access [flags]

Options

  -h, --help                      help for grant-access
      --org-id string             The ID of the org to grant access to.
      --private-model-id string   The ID of the private model to grant access to.

co admin private-model list

List names of available private models.

co admin private-model list [flags]

Options

  -h, --help   help for list

co admin private-model revoke-access

Revoke an org's access to a private model.

co admin private-model revoke-access [flags]

Options

  -h, --help                      help for revoke-access
      --org-id string             The ID of the org to grant access to.
      --private-model-id string   The ID of the private model to grant access to.

co admin private-model update

Update an existing private model.

co admin private-model update [id] [flags]

Options

      --bert-batching-parameters-file string   path to BERT batching parameters file
      --bert-path string                       path to BERT model
      --cpu string                             Amount of cpu to allot to model
      --encoder-dir string                     Path to encoder (default "gs://cohere-prod/encoders/coheretext50k-30Mplus1")
      --gpt-batching-parameters-file string    path to GPT batching parameters file
      --gpt-path string                        path to GPT model
      --gpu string                             Amount of gpu to allot to model
  -h, --help                                   help for update
      --max int32                              maximum replicas (default 10)
      --max-bert-tokens int                    maximum token length for BERT model (default 1024)
      --max-gpt-tokens int                     maximum token length for GPT model (default 1024)
      --mem string                             Amount of memory to allot to model
      --min int32                              minimum replicas (default 1)
      --replicas int                           how many replicas to create (don't use if autoscaling)
      --route string                           path to GPT model
      --target-gpu string                      target gpu utilization (%), set to 0 to not scale based off this (default "65")

co admin sync

Options

  -h, --help   help for sync

co admin sync stripe

sync an organization's usage to Stripe

co admin sync stripe [flags]

Options

  -h, --help   help for stripe