langtest.modelhandler.lmstudio_modelhandler.PretrainedModelForNER#

class PretrainedModelForNER(model: Any, output_parser: Callable | None = None, **kwargs)#

Bases: PretrainedModel, ModelAPI

A class representing a pretrained model for named entity recognition.

Inherits:

PretrainedModel: The base class for pretrained models.

predict(text: str, \*args, \*\*kwargs)#

Predicts the answer to a given question based on the pre-trained model.

Raises:

Exception – If an error occurs during prediction.

__init__(model: Any, output_parser: Callable | None = None, **kwargs) → None#

Initialize the PretrainedModel.

Parameters:

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

• **kwargs – Additional keyword arguments.

Methods

__init__(model[, output_parser])	Initialize the PretrainedModel.
load_model(path, *args, **kwargs)	Load the pretrained model.
predict(text, *args, **kwargs)	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, *args, **kwargs) → NEROutput#

Perform prediction using the pretrained model.

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