Update app.py

app.py

@@ -229,8 +229,7 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                     gr.Examples(
                         examples=video_examples,
                         inputs=[video_query, video_upload]
-                    )
-                    
+                    ) 
             with gr.Accordion("Advanced options", open=False):
                 max_new_tokens = gr.Slider(label="Max new tokens", minimum=1, maximum=MAX_MAX_NEW_TOKENS, step=1, value=DEFAULT_MAX_NEW_TOKENS)
                 temperature = gr.Slider(label="Temperature", minimum=0.1, maximum=4.0, step=0.1, value=0.6)
@@ -240,11 +239,11 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                 
         with gr.Column():
             with gr.Column(elem_classes="canvas-output"):
-            gr.Markdown("## Result.Md")
-            output = gr.Textbox(label="Raw Output", interactive=False, lines=2, scale=2)
+                gr.Markdown("## Result.Md")
+                output = gr.Textbox(label="Raw Output", interactive=False, lines=2, scale=2)
             
-            with gr.Accordion("Formatted Result", open=False):
-                markdown_output = gr.Markdown()
+                with gr.Accordion("Formatted Result", open=False):
+                    markdown_output = gr.Markdown()
                 
             model_choice = gr.Radio(
                 choices=["Qwen2.5-VL-7B-Instruct", "Qwen2.5-VL-3B-Instruct"],
@@ -254,7 +253,8 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
             gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Qwen2.5-VL/discussions)")
             gr.Markdown("> [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct): The Qwen2.5-VL-7B-Instruct model is a multimodal AI model developed by Alibaba Cloud that excels at understanding both text and images. It's a Vision-Language Model (VLM) designed to handle various visual understanding tasks, including image understanding, video analysis, and even multilingual support.")
             gr.Markdown("> [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct): Qwen2.5-VL-3B-Instruct is an instruction-tuned vision-language model from Alibaba Cloud, built upon the Qwen2-VL series. It excels at understanding and generating text related to both visual and textual inputs, making it capable of tasks like image captioning, visual question answering, and object localization. The model also supports long video understanding and structured data extraction")
-
+            gr.Markdown(">⚠️note: all the models in space are not guaranteed to perform well in video inference use cases.")
+            
     image_submit.click(
         fn=generate_image,
         inputs=[model_choice, image_query, image_upload, max_new_tokens, temperature, top_p, top_k, repetition_penalty],