nemo_microservices.types.v2.models.model_create_params#

Module Contents#

Classes#

API#

class nemo_microservices.types.v2.models.model_create_params.ModelCreateParams#

Bases: typing_extensions.TypedDict

api_endpoint: nemo_microservices.types.shared_params.api_endpoint_data.APIEndpointData#

None

Data about an API endpoint.

artifact: nemo_microservices.types.shared_params.model_artifact.ModelArtifact#

None

Data about a model artifact (a set of checkpoint files, configs, and other auxiliary info).

The files_url field can point to a DataStore location.

Example:

  • nds://models/rdinu/my-lora-customization

The rdinu/my-lora-customization part above is the actual repository.

If a specific revision needs to be referred, the HuggingFace syntax is used.

  • nds://models/rdinu/my-lora-customization@v1

  • nds://models/rdinu/my-lora-customization@8df79a8

base_model: str#

None

Link to another model which is used as a base for the current model

custom_fields: Dict[str, object]#

None

Custom fields for additional metadata

description: str#

None

Optional description of the model

guardrails: nemo_microservices.types.shared_params.guardrail_config_param.GuardrailConfigParam#

None

A guardrail configuration

model_providers: nemo_microservices._types.SequenceNotStr[str]#

None

List of ModelProvider namespace/name resource names that provide inference for this Model Entity

name: typing_extensions.Required[str]#

None

Name of the model entity

namespace: str#

None

The namespace of the model entity

ownership: Dict[str, object]#

None

Ownership information for the model

peft: nemo_microservices.types.shared_params.parameter_efficient_finetuning_data.ParameterEfficientFinetuningData#

None

Data about a parameter-efficient finetuning.

project: str#

None

The URN of the project associated with this model entity

prompt: nemo_microservices.types.shared_params.prompt_data.PromptData#

None

Prompt engineering data.

spec: nemo_microservices.types.shared_params.model_spec.ModelSpec#

None

Detailed specification about a model.