Update app.py

app.py

@@ -531,6 +531,18 @@ if __name__ == "__main__":
                     placeholder="Enter text to summarize, the text will be cleaned and truncated on Spaces. Narrative, academic (both papers and lecture transcription), and article text work well. May take a bit to generate depending on the input text :)",
                 )
         gr.Markdown("---")
+        gr.Markdown("# Document Summarization with Long-Document Transformers")
+        gr.Markdown(
+            """An example use case for fine-tuned long document transformers. Model(s) are trained on [book summaries](https://hf.co/datasets/kmfoda/booksum). Architectures [in this demo](https://hf.co/spaces/pszemraj/document-summarization) are [LongT5-base](https://hf.co/pszemraj/long-t5-tglobal-base-16384-book-summary) and [Pegasus-X-Large](https://hf.co/pszemraj/pegasus-x-large-book-summary).
+
+            **Want more performance? Run this demo from a free Google Colab GPU:**.
+            <br>
+            <a href="https://colab.research.google.com/gist/pszemraj/52f67cf7326e780155812a6a1f9bb724/document-summarization-on-gpu.ipynb">
+            <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+            </a>
+            <br>
+            """
+        )
         with gr.Column():
             gr.Markdown("## Generate Summary")
             with gr.Row():
@@ -634,16 +646,16 @@ if __name__ == "__main__":
                 )
         with gr.Column():
             gr.Markdown("## About")
-            # gr.Markdown(
-            #     "- Models are fine-tuned on the [🅱️ookSum dataset](https://arxiv.org/abs/2105.08209). The goal was to create a model that generalizes well and is useful for summarizing text in academic and everyday use."
-            # )
-            # gr.Markdown(
-            #     "- _Update April 2023:_ Additional models fine-tuned on the [PLOS](https://hf.co/datasets/pszemraj/scientific_lay_summarisation-plos-norm) and [ELIFE](https://hf.co/datasets/pszemraj/scientific_lay_summarisation-elife-norm) subsets of the [scientific lay summaries](https://arxiv.org/abs/2210.09932) dataset are available (see dropdown at the top)."
-            # )
-            # gr.Markdown(
-            #     "Adjust the max input words & max PDF pages for OCR by duplicating this space and [setting the environment variables](https://hf.co/docs/hub/spaces-overview#managing-secrets) `APP_MAX_WORDS` and `APP_OCR_MAX_PAGES` to the desired integer values."
-            # )
-            # gr.Markdown("---")
+            gr.Markdown(
+                "- Models are fine-tuned on the [🅱️ookSum dataset](https://arxiv.org/abs/2105.08209). The goal was to create a model that generalizes well and is useful for summarizing text in academic and everyday use."
+            )
+            gr.Markdown(
+                "- _Update April 2023:_ Additional models fine-tuned on the [PLOS](https://hf.co/datasets/pszemraj/scientific_lay_summarisation-plos-norm) and [ELIFE](https://hf.co/datasets/pszemraj/scientific_lay_summarisation-elife-norm) subsets of the [scientific lay summaries](https://arxiv.org/abs/2210.09932) dataset are available (see dropdown at the top)."
+            )
+            gr.Markdown(
+                "Adjust the max input words & max PDF pages for OCR by duplicating this space and [setting the environment variables](https://hf.co/docs/hub/spaces-overview#managing-secrets) `APP_MAX_WORDS` and `APP_OCR_MAX_PAGES` to the desired integer values."
+            )
+            gr.Markdown("---")
 
         load_examples_button.click(
             fn=load_single_example_text, inputs=[example_name], outputs=[input_text]