Add SimMIM (#15586)

* Add first draft

* Make model importable

* Make SwinForMaskedImageModeling importable

* Fix imports

* Add missing inits

* Add support for Swin

* Fix bug

* Fix bug

* Fix another bug

* Fix Swin MIM implementation

* Fix default encoder stride

* Fix Swin

* Add print statements for debugging

* Add image_size data argument

* Fix Swin

* Fix image_size

* Add print statements for debugging

* Fix print statement

* Remove print statements

* Improve reshaping of bool_masked_pos

* Add support for DeiT, fix tests

* Improve docstrings

* Apply new black version

* Improve script

* Fix bug

* Improve README

* Apply suggestions from code review

* Remove DS_Store and add to gitignore

* Apply suggestions from code review + fix BEiT Flax

* Revert BEiT changes

* Improve README

* Fix code quality

* Improve README

Co-authored-by: Niels Rogge <nielsrogge@Nielss-MBP.localdomain>
Co-authored-by: Niels Rogge <nielsrogge@Nielss-MacBook-Pro.local>

docs/source/model_doc/auto.mdx

@@ -142,6 +142,10 @@ Likewise, if your `NewModel` is a subclass of [`PreTrainedModel`], make sure its
 
 [[autodoc]] AutoModelForAudioXVector
 
+## AutoModelForMaskedImageModeling
+
+[[autodoc]] AutoModelForMaskedImageModeling
+
 ## AutoModelForObjectDetection
 
 [[autodoc]] AutoModelForObjectDetection

docs/source/model_doc/deit.mdx

@@ -86,6 +86,11 @@ This model was contributed by [nielsr](https://huggingface.co/nielsr).
 [[autodoc]] DeiTModel
     - forward
 
+## DeiTForMaskedImageModeling
+
+[[autodoc]] DeiTForMaskedImageModeling
+    - forward
+
 ## DeiTForImageClassification
 
 [[autodoc]] DeiTForImageClassification

docs/source/model_doc/swin.mdx

@@ -53,6 +53,10 @@ This model was contributed by [novice03](https://huggingface.co/novice03>). The
 [[autodoc]] SwinModel
     - forward
 
+## SwinForMaskedImageModeling
+
+[[autodoc]] SwinForMaskedImageModeling
+    - forward
 
 ## SwinForImageClassification
 

docs/source/model_doc/vit.mdx

@@ -103,6 +103,11 @@ go to him!
 [[autodoc]] ViTModel
     - forward
 
+## ViTForMaskedImageModeling
+
+[[autodoc]] ViTForMaskedImageModeling
+    - forward
+
 ## ViTForImageClassification
 
 [[autodoc]] ViTForImageClassification