Automated compatible models list for task guides (#21338)

* initial commit. added tip placeholders and a script

* removed unused imports, fixed paths

* fixed generated links

* make style

* split language modeling doc into two: causal language modeling and masked language modeling

* added check_task_guides.py to make fix-copies

* review feedback addressed

docs/source/en/tasks/object_detection.mdx

@@ -21,11 +21,6 @@ be present in different parts of an image (e.g. the image can have several cars)
 This task is commonly used in autonomous driving for detecting things like pedestrians, road signs, and traffic lights.
 Other applications include counting objects in images, image search, and more.
 
- <Tip>
-Check out the <a href="https://huggingface.co/tasks/object-detection">object detection</a> task page to learn about use cases,
-models, metrics, and datasets associated with this task.
- </Tip>
-
 In this guide, you will learn how to:
 
  1. Finetune [DETR](https://huggingface.co/docs/transformers/model_doc/detr), a model that combines a convolutional
@@ -33,6 +28,17 @@ In this guide, you will learn how to:
  dataset.
  2. Use your finetuned model for inference.
 
+<Tip>
+The task illustrated in this tutorial is supported by the following model architectures:
+
+<!--This tip is automatically generated by `make fix-copies`, do not fill manually!-->
+
+[Conditional DETR](../model_doc/conditional_detr), [Deformable DETR](../model_doc/deformable_detr), [DETR](../model_doc/detr), [Table Transformer](../model_doc/table-transformer), [YOLOS](../model_doc/yolos)
+
+<!--End of the generated tip-->
+
+</Tip>
+
 Before you begin, make sure you have all the necessary libraries installed:
 
 ```bash