emmi.modules.attention.anchor_attention.self_anchor_attention
=============================================================

.. py:module:: emmi.modules.attention.anchor_attention.self_anchor_attention


Classes
-------

.. autoapisummary::

   emmi.modules.attention.anchor_attention.self_anchor_attention.SelfAnchorAttention


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

.. py:class:: SelfAnchorAttention(config)

   Bases: :py:obj:`emmi.modules.attention.anchor_attention.multi_branch_anchor_attention.MultiBranchAnchorAttention`


   Anchor attention within branches: each configured branch attends to its own anchors independently.

   For a list of branches (e.g., A, B, C), this creates a pattern where A tokens attend to A_anchors,
   B tokens attend to B_anchors, and C tokens attend to C_anchors.
   It requires all configured branches and their anchors to be present in the input.

   Example: surface tokens attend to surface_anchors and volume tokens attend to volume_anchors.
   This is achieved via the following attention patterns:
       AttentionPattern(query_tokens=["surface_anchors", "surface_queries"], key_value_tokens=["surface_anchors"])
       AttentionPattern(query_tokens=["volume_anchors", "volume_queries"], key_value_tokens=["volume_anchors"])

   :param dim: Model dimension.
   :param num_heads: Number of attention heads.
   :param use_rope: Whether to use rotary position embeddings.
   :param bias: Whether to use bias in the linear projections.
   :param init_weights: Weight initialization method.
   :param branches: A sequence of all participating branch names.
   :param anchor_suffix: Suffix identifying anchor tokens.

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