nemo_microservices.types.customization.dataset_parameters_param#

Module Contents#

Classes#

API#

class nemo_microservices.types.customization.dataset_parameters_param.DatasetParametersParam#

Bases: typing_extensions.TypedDict

in_batch_negatives: bool#

None

In-batch negatives treats every other example in a training batch as a negative sample during contrastive learning. When enabled, the model learns to distinguish the correct positive pair not just from explicitly provided hard negatives, but from all other examples in the same batch. This can improve training without adding extra labeled negative data.

negative_sample_strategy: str#

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

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

  • Embedding Only

tools: Iterable[nemo_microservices.types.customization.tool_schema_param.ToolSchemaParam]#

None

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