Toxicity Detection model

[rlucatoor]

What is a Toxicity Detection model

A Toxicity Detection model identifies whether a piece of text is unwelcome and, if so, for which reason.

What needs to be done

Implement a Toxicity Detection model that exposes the following public methods:

.train() method:

.train(output_path: Optional[str] = None, num_samples: int = config.DEFAULT_SYNTHEX_DATAPOINT_NUM, num_epochs: int = 3)`

The method should train the model to assign one of the following labels

• safe
• toxic
• insulting
• threatening
• obscene
• identity-attack
• other-unsafe

to any piece of text.

.__call__(text: Union[str, list[str])

• If a str is provided, the model should return any one of the labels listed above.

• If a list[str] is provided, the model should return a list of labels, one per sentence.

.load(model_path: str)

Loads a pre-trained Toxicity Detection model from the specified path.