noether.modeling.modules.attention.anchor_attention.multi_branch
================================================================

.. py:module:: noether.modeling.modules.attention.anchor_attention.multi_branch


Exceptions
----------

.. autoapisummary::

   noether.modeling.modules.attention.anchor_attention.multi_branch.MissingBranchTokensError
   noether.modeling.modules.attention.anchor_attention.multi_branch.MissingAnchorTokenError
   noether.modeling.modules.attention.anchor_attention.multi_branch.UnexpectedTokenError


Classes
-------

.. autoapisummary::

   noether.modeling.modules.attention.anchor_attention.multi_branch.MultiBranchAnchorAttention


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

.. py:exception:: MissingBranchTokensError

   Bases: :py:obj:`ValueError`


   Raised when expected tokens for a configured branch are not present.

   Initialize self.  See help(type(self)) for accurate signature.


.. py:exception:: MissingAnchorTokenError

   Bases: :py:obj:`ValueError`


   Raised when a required anchor token is not present.

   Initialize self.  See help(type(self)) for accurate signature.


.. py:exception:: UnexpectedTokenError

   Bases: :py:obj:`ValueError`


   Raised when an unexpected token is present.

   Initialize self.  See help(type(self)) for accurate signature.


.. py:class:: MultiBranchAnchorAttention(config)

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


   A base class for multi-branch anchor-based attention modules with shared parameters between branches.

   Anchor attention limits the self-attention to anchor tokens while other tokens use cross-attention.
   Multiple branches for different modalities use the same linear-projection parameters.
   This base class provides a common constructor, validation logic, and forward method implementation.
   Subclasses only need to implement `_create_attention_patterns` to define their specific attention patterns.

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: mixed_attention


   .. py:attribute:: branches
      :value: None



   .. py:attribute:: anchor_suffix
      :value: None



   .. py:method:: forward(x, token_specs, freqs = None)

      Apply attention using the patterns defined by the subclass.