# Transformer Models

Attention-based architectures for time-series representation learning.

## TST

Transformer-based model with masked reconstruction pretraining. Uses `BasicEncodingMixin` for inference.

```{eval-rst}
.. automodule:: chronocratic.models.transformer.tst.model
   :members:
   :show-inheritance:

.. automodule:: chronocratic.models.transformer.tst.config
   :members:
   :show-inheritance:
```