langtest.modelhandler.lmstudio_modelhandler.PretrainedModelForSensitivity#

class PretrainedModelForSensitivity(model: Any, *args, **kwargs)#

Bases: PretrainedModel, ModelAPI

__init__(model: Any, *args, **kwargs)#

Initialize the PretrainedModelForSensitivity.

Parameters:

• model (Any) – The pretrained model to be used.

• *args – Additional positional arguments.

• **kwargs – Additional keyword arguments.

Methods

__init__(model, *args, **kwargs)	Initialize the PretrainedModelForSensitivity.
load_model(path, *args, **kwargs)	Load the pretrained model.
predict(text, prompt, server_prompt, *args, ...)	Perform prediction using the pretrained model.
predict_raw(text, prompt, server_prompt, ...)	Predicts the output for the given input text without caching.

Attributes

model_registry

classmethod load_model(path: str, *args, **kwargs) → Any#

Load the pretrained model.

Parameters:

• path (str) – The path to the pretrained model.

• *args – Additional positional arguments.

• **kwargs – Additional keyword arguments.

Returns:

The loaded pretrained model.

Return type:

Any

predict(text: str | dict, prompt: dict, server_prompt: str, *args, **kwargs)#

Perform prediction using the pretrained model.

Parameters:

• text (Union[str, dict]) – The input text or dictionary.

• server_prompt (str) – The server prompt for the chat.

• *args – Additional positional arguments.

• **kwargs – Additional keyword arguments.

Returns:

A dictionary containing the prediction result.

• ’result’: The prediction result.

Return type:

dict

predict_raw(text: str | dict, prompt: dict, server_prompt: str, *args, **kwargs)#

Predicts the output for the given input text without caching.

Parameters:

• text (Union[str, dict]) – The input text or dictionary.

• prompt (dict) – The prompt for the prediction.

• server_prompt (str) – The server prompt for the chat.

• *args – Additional positional arguments.

• **kwargs – Additional keyword arguments.

Returns:

The predicted output.

Return type:

str