TokenSearcherPredictor

Predictor for knowledgator/UTC models

This predictor is specifically build for knowledgator/UTC models. For more details about models, see:

knowledgator/UTC-DeBERTa-large · Hugging Facehuggingface

Universal token classification - a knowledgator Collectionhuggingface

About use cases and more, see:

As GPT4 but for token classificationMedium

Try it on our Hugging Face space:

0 Shot NER - a Hugging Face Space by knowledgatorhuggingface

Subclass of TransformersPipeline.

Module: implementation.predictors

Methods and properties

Main methods and properties

---

__init__

Arguments:

• cfg (Optional[TransformersPipelineConfig], optional): Configuration for predictor. If value equals to None, default TokenSearcherPredictorConfig configuration will be used. Defaults to None.
• input_class (Type[Input], optional): Class for input validation. Defaults to TokenSearcherPredictorInput.
• output_class (Type[Output], optional): Class for output validation. Defaults to TokenSearcherPredictorOutput.
• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

TokenSearcherPredictorConfig

Prebuild configuration that describes default parameters for knowledgator/UTC models pipeline. Subclass of TransformersPipelineConfig. It contains all parameters described in TransformersPipelineConfig but overwrites some default values that described here.

---

__init__

Arguments:

• task (Optional[str], optional): Pipeline task. Defaults to "ner".

• model (Optional[Union[str, PreTrainedModel, TFPreTrainedModel]], optional): Model that will be used. Defaults to "knowledgator/UTC-DeBERTa-small".
• kwargs (Optional[Dict[str, Any]], optional): Extra parameters. Defaults to

{
    "aggregation_strategy": "first", 
    "batch_size": 12
}

• ...

For other parameters, see TransformersPipelineConfig.

---

---

---

TokenSearcherPredictorInput

Subclass of TransformersBasicInput.

---

__init__

Arguments:

• inputs (List[str]): Text inputs.

---

---

---

TokenSearcherPredictorOutput

Subclass of TransformersBasicOutput.

---

__init__

Arguments:

• output (List[List[Dict[str, Any]]]): Entities of corresponding inputs.

---

---