logitorch.models.fairr
======================

.. py:module:: logitorch.models.fairr


Classes
-------

.. autoapisummary::

   logitorch.models.fairr.FactSelector
   logitorch.models.fairr.FaiRR
   logitorch.models.fairr.KnowledgeComposer
   logitorch.models.fairr.RuleSelector


Module Contents
---------------

.. py:class:: FactSelector(pretrained_roberta_model: str)

   Bases: :py:obj:`torch.nn.Module`


   FactSelector is a class that represents a fact-based selector model.
   It uses a pretrained RoBERTa model for encoding input sequences and a linear classifier for prediction.


   .. py:method:: forward(x, y=None)

      Forward pass of the FactSelector model.

      Args:
          x (dict): Input dictionary containing the input sequences.
          y (None): Placeholder for compatibility with other models.

      Returns:
          None: This method is not implemented.



   .. py:attribute:: classifier


   .. py:attribute:: dropout


   .. py:attribute:: model


   .. py:attribute:: out_dim


   .. py:attribute:: tokenizer


.. py:class:: FaiRR

   Bases: :py:obj:`torch.nn.Module`


   FaiRR is a class that represents the FaiRR model, which combines rule-based and fact-based selectors.


.. py:class:: KnowledgeComposer(pretrained_t5_model: str)

   Bases: :py:obj:`torch.nn.Module`


   KnowledgeComposer is a class that represents a knowledge composer model.
   It uses a pretrained T5 model for generating text based on input prompts.


   .. py:attribute:: model


   .. py:attribute:: tokenizer


.. py:class:: RuleSelector(pretrained_roberta_model: str, cls_dropout=0.1)

   Bases: :py:obj:`torch.nn.Module`


   RuleSelector is a class that represents a rule-based selector model.
   It uses a pretrained RoBERTa model for encoding input sequences and a linear classifier for prediction.


   .. py:method:: forward(x, y=None)

      Forward pass of the RuleSelector model.

      Args:
          x (dict): Input dictionary containing the input sequences.
          y (None): Placeholder for compatibility with other models.

      Returns:
          torch.Tensor: Logits representing the predicted scores.



   .. py:attribute:: classifier


   .. py:attribute:: dropout


   .. py:attribute:: model


   .. py:attribute:: out_dim


   .. py:attribute:: tokenizer