Update Model

The organization ID for request, it override the x-org-id header if set.

LLM model id which is supported by tune.Studio or any huggingface model.

The time the model was created.

feature gates for the model (internal use).

The id of the model.

The name of the model.

true if model have public endpoint else false.

number of replicas for the model.

Used to specify the resource requirement for a (job, model).

server type of the model, if empty used from DB.

State of the model. This is used to track the model's lifecycle. The state is updated by the model controller.

tracker id of the for model analytics.

The time the model was last updated.

uri of the model in the form of username/model_name.

Hostname of the endpoint.

Model or Serving (Group) ID.

URL to access the model or serving group.

deprecated.

metadata for the model.

• MODALITY_TEXT: Text.
• MODALITY_IMAGE: Image.
• MODALITY_AUDIO: Audio.
• MODALITY_VIDEO: Video.
• MODALITY_IMAGE_TEXT: Image and Text.

• QUANTIZATION_AWQ: Aware Quantization.
• QUANTIZATION_GPTQ: GPT Quantization.
• QUANTIZATION_SQUEEZELLM: SqueezeLLM Quantization.
• QUANTIZATION_FP16: FP16 Quantization.

CPU in milli-core.

GPU Type.

Number of GPUs.

max number of retries for a job.

Memory in MiB.

in seconds. Note this is inclusive of jobs and init containers, enforced by k8s, regardless of max_retries set. Not supported for models.

extra message for the state.

State of the model.

• UNSPECIFIED: Model in unknown state.
• PROVISIONING: model is being created on the cluster.
• ENV_SETUP: running initilization steps.
• AWAITING_STARTUP: starting model container.
• LIVENESS_CHECK: checking model liveness.
• READY: model is ready.
• FAILED: model is in error state.
• TERMINATED: model is terminated can be restarted.