nemo_microservices.types.evaluation_params_param#

Module Contents#

Classes#

API#

class nemo_microservices.types.evaluation_params_param.EvaluationParamsParam#

Bases: typing_extensions.TypedDict

extra: Dict[str, object]#

None

Any other custom parameters.

limit_samples: int#

None

Limit number of evaluation samples

max_retries: int#

None

Maximum number of retries for failed requests.

max_tokens: int#

None

The maximum number of tokens to generate.

parallelism: int#

None

Parallelism to be used for the evaluation job.

Typically, this represents the maximum number of concurrent requests made to the model.

request_timeout: int#

None

The timeout to be used for requests made to the model.

stop: str | nemo_microservices._types.SequenceNotStr[str]#

None

Up to 4 sequences where the API will stop generating further tokens.

temperature: float#

None

Float value between 0 and 1.

temp of 0 indicates greedy decoding, where the token with highest prob is chosen. Temperature can’t be set to 0.0 currently.

top_p: float#

None

Float value between 0 and 1; limits to the top tokens within a certain probability. top_p=0 means the model will only consider the single most likely token for the next prediction.