layers.rope_frequenty_config
============================

.. py:module:: layers.rope_frequenty_config


Classes
-------

.. autoapisummary::

   layers.rope_frequenty_config.RopeFrequencyConfig


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

.. py:class:: RopeFrequencyConfig(/, **data)

   Bases: :py:obj:`pydantic.BaseModel`


   Configuration for RoPE frequency settings.

   Create a new model by parsing and validating input data from keyword arguments.

   Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
   validated to form a valid model.

   `self` is explicitly positional-only to allow `self` as a field name.


   .. py:attribute:: hidden_dim
      :type:  int
      :value: None


      Dimensionality of frequencies (in transformers this should be the head dimension).


   .. py:attribute:: input_dim
      :type:  int
      :value: None


      Dimensionality of the coordinates (e.g., 2 for 2D coordinates, 3 for 3D coordinates).


   .. py:attribute:: max_wavelength
      :type:  int
      :value: None


      10000.0

      :type: Theta parameter for the transformer sine/cosine embedding. Default


   .. py:attribute:: assert_positive
      :type:  bool
      :value: None


      True

      :type: Makes sure that coordinates were rescaled to be positive only. Default


   .. py:attribute:: implementation
      :type:  Literal['real', 'complex']
      :value: None


      "real" -> basic implementation using real coordinates (this is slow and only here for backward compatibility).
      "complex" -> fast implementation of rotation via complex multiplication. Default: "real".