Add MAE (#15120)

* First draft

* More improvements

* More improvements

* More improvements

* Fix embeddings

* Add conversion script

* Finish conversion script

* More improvements

* Fix forward pass

* Remove print statements

* Add weights initialization

* Add initialization of decoder weights

* Add support for other models in the conversion script

* Fix patch_size for huge model

* Fix most of the tests

* Fix integration test

* Fix docs

* Fix archive_list

* Apply suggestions from code review

* Improve documentation

* Apply more suggestions

* Skip some tests due to non-deterministic behaviour

* Fix test_initialization

* Remove unneccessary initialization of nn.Embedding

* Improve docs

* Fix dummies

* Remove ViTMAEFeatureExtractor from docs

* Add model to README and table of contents

* Delete inference file

docs/source/_toctree.yml

@@ -288,6 +288,8 @@
       title: Vision Text Dual Encoder
     - local: model_doc/vit
       title: Vision Transformer (ViT)
+    - local: model_doc/vit_mae
+      title: ViTMAE
     - local: model_doc/visual_bert
       title: VisualBERT
     - local: model_doc/wav2vec2