nat.experimental.test_time_compute.models.editor_config#
Classes#
Configuration for the LLMAsAJudgeEditor. |
|
Configuration for an 'iterative plan refinement' strategy. |
|
Configuration for the MotivationAwareSummarization strategy. |
Module Contents#
- class LLMAsAJudgeEditorConfig(/, **data: Any)#
Bases:
nat.data_models.ttc_strategy.TTCStrategyBaseConfig
Configuration for the LLMAsAJudgeEditor.
Create a new model by parsing and validating input data from keyword arguments.
Raises [
ValidationError
][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.self
is explicitly positional-only to allowself
as a field name.- editing_llm: nat.data_models.component_ref.LLMRef | Any | None = None#
- feedback_llm: nat.data_models.component_ref.LLMRef | Any | None = None#
- class IterativePlanRefinementConfig(/, **data: Any)#
Bases:
nat.data_models.ttc_strategy.TTCStrategyBaseConfig
Configuration for an ‘iterative plan refinement’ strategy.
Create a new model by parsing and validating input data from keyword arguments.
Raises [
ValidationError
][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.self
is explicitly positional-only to allowself
as a field name.- editor_llm: nat.data_models.component_ref.LLMRef | Any | None = None#
- class MotivationAwareSummarizationConfig(/, **data: Any)#
Bases:
nat.data_models.ttc_strategy.TTCStrategyBaseConfig
Configuration for the MotivationAwareSummarization strategy.
Create a new model by parsing and validating input data from keyword arguments.
Raises [
ValidationError
][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.self
is explicitly positional-only to allowself
as a field name.- editor_llm: nat.data_models.component_ref.LLMRef | Any | None = None#