DOC: add fact. embedding to API

JeanKossaifi · JeanKossaifi · commit e150f776b67e · 2022-12-30T19:26:53.000+01:00
diff --git a/doc/user_guide/factorized_embeddings.rst b/doc/user_guide/factorized_embeddings.rst
@@ -16,5 +16,7 @@ input and output tensorized shapes, to have 3 dimensions each:
 
 Or, you can create it by decomposing an existing embedding layer:
 
+.. code-block:: python
+
     from_embedding = tltorch.FactorizedEmbedding.from_embedding(embedding_layer, auto_reshape=True,
                 factorization='blocktt', n_tensorized_modes=3, rank=0.4)
diff --git a/doc/user_guide/index.rst b/doc/user_guide/index.rst
@@ -13,4 +13,5 @@ It builds on top of `TensorLy <tensorly.org>`_ and enables anyone to use tensor
    trl
    factorized_conv
    tensorized_linear
+   factorized_embeddings
    tensor_hooks
