models-alias
post/bodhi/v1/models/alias

Request

  • Base URL: http://localhost:1135
  • URL: http://localhost:1135/bodhi/v1/models/alias
  • Auth: one of:
    • HTTP bearer
    • HTTP bearer
    • OAuth 2 (authorization code, authorization URL /bodhi/v1/auth/initiate, token URL /bodhi/v1/auth/callback, scopes: resource_power_user)

Request body

aliasstring required

Alias name — unique per (tenant_id, user_id) scope

repostring required

Repository in format "user/repo"

filenamestring required

Filename of the GGUF model

snapshotstring nullable

Snapshot/commit identifier (optional — defaults to latest available)

context_paramsstring[] nullable

Context parameters for the model

Example request

{
  "alias": "llama3:instruct",
  "context_params": [
    "--ctx-size 4096"
  ],
  "filename": "Meta-Llama-3-8B-Instruct.Q4_K_M.gguf",
  "repo": "QuantFactory/Meta-Llama-3-8B-Instruct-GGUF",
  "request_params": {
    "temperature": 0.7
  }
}

Response

Alias created succesfully

idstring required
aliasstring required
repostring required
filenamestring required
snapshotstring required
sourcestring required
accessboolean required

Whether the current principal may run inference on this model.

model_paramsobject required
context_paramsstring[] required
created_atstring date-time required
updated_atstring date-time required
sizeinteger nullable

Local GGUF file size in bytes (present when the file is resolvable on disk)

Changes

    • info

      added the required property to the response with the status

    • info

      added the new optional request property /////

    • info

      added the optional property / to the response with the status