Optional. The Google Cloud Storage location to write the artifacts.
deployToSameEndpoint
boolean
Optional. By default, bison to gemini migration will always create new model/endpoint, but for gemini-1.0 to gemini-1.5 migration, we default deploy to the same endpoint. See details in this Section.
Response body
If successful, the response body contains an instance of Operation.
TunedModelRef
TunedModel Reference for legacy model migration.
Fields
tuned_model_ref
Union type
The Tuned Model Reference for the model. tuned_model_ref can be only one of the following:
tunedModel
string
Support migration from model registry.
tuningJob
string
Support migration from tuning job list page, from gemini-1.0-pro-002 to 1.5 and above.
pipelineJob
string
Support migration from tuning job list page, from bison model to gemini model.
JSON representation
{// tuned_model_ref"tunedModel": string,"tuningJob": string,"pipelineJob": string// Union type}
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-06-27 UTC."],[],[],null,["# Method: tuningJobs.rebaseTunedModel\n\n**Full name**: projects.locations.tuningJobs.rebaseTunedModel\n\nRebase a TunedModel. \n\n### Endpoint\n\npost `https:``/``/{service-endpoint}``/v1beta1``/{parent}``/tuningJobs:rebaseTunedModel` \nWhere `{service-endpoint}` is one of the [supported service endpoints](/vertex-ai/docs/reference/rest#rest_endpoints).\n\n### Path parameters\n\n`parent` `string` \nRequired. The resource name of the Location into which to rebase the Model. Format: `projects/{project}/locations/{location}`\n\n### Request body\n\nThe request body contains data with the following structure:\nFields `tunedModelRef` `object (`[TunedModelRef](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.tuningJobs/rebaseTunedModel#TunedModelRef)`)` \nRequired. TunedModel reference to retrieve the legacy model information.\n`tuningJob` `object (`[TuningJob](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.tuningJobs#TuningJob)`)` \nOptional. The TuningJob to be updated. Users can use this TuningJob field to overwrite tuning configs.\n`artifactDestination` `object (`[GcsDestination](/vertex-ai/docs/reference/rest/v1beta1/GcsDestination)`)` \nOptional. The Google Cloud Storage location to write the artifacts.\n`deployToSameEndpoint` `boolean` \nOptional. By default, bison to gemini migration will always create new model/endpoint, but for gemini-1.0 to gemini-1.5 migration, we default deploy to the same endpoint. See details in this Section. \n\n### Response body\n\nIf successful, the response body contains an instance of [Operation](/vertex-ai/docs/reference/rest/Shared.Types/ListOperationsResponse#Operation).\n\nTunedModelRef\n-------------\n\nTunedModel Reference for legacy model migration.\nFields \n`tuned_model_ref` `Union type` \nThe Tuned Model Reference for the model. `tuned_model_ref` can be only one of the following:\n`tunedModel` `string` \nSupport migration from model registry.\n`tuningJob` `string` \nSupport migration from tuning job list page, from gemini-1.0-pro-002 to 1.5 and above.\n`pipelineJob` `string` \nSupport migration from tuning job list page, from bison model to gemini model."]]
