Update app.py

app.py

@@ -44,6 +44,16 @@ with gr.Blocks(theme="sudeepshouche/minimalist") as demo:
                 inputs=textbox
             )
             submit_button = gr.Button("Submit")
+
+                        gr.Markdown("""
+            Where to get started with Vision Language Models:
+            
+            - [Hugging Face overview of Vision Language Models](https://huggingface.co/blog/vlms#overview-of-open-source-vision-language-models)
+            - [Blog Post on PaliGemma Model Capabilities and Use Cases](https://huggingface.co/blog/paligemma#model-capabilities)
+            
+            Keep an eye on the evolution of the evolution of the [Model Explorer from Google](https://ai.google.dev/edge/model-explorer#two_ways_to_use_model_explorer).  It didn't work initially for some of the VLM "fusion" model types I was looking at, but certainly a great tool for the right model.
+            """)
+            
         with gr.Column():
             output = gr.Textbox(label="Model Architecture", lines=20, placeholder="Model architecture will appear here...", show_copy_button=True)
             error_output = gr.Textbox(label="Error", lines=10, placeholder="Exceptions will appear here...", show_copy_button=True)