DatasetParameters#

class nemo_microservices.types.customization.DatasetParameters(*args: Any, **kwargs: Any)

Bases: BaseModel

negative_sample_strategy: str | None = None

How to select negatives when more are available than needed - Embedding Only.

‘first’ picks the first N; ‘random’ samples N negatives randomly.

num_hard_negatives: int | None = None

Number of negative documents to include per query for contrastive training.

  • Embedding Only

tools: List[ToolSchema] | None = None

A list of tools that are available for training with tool calling