Update app.py

app.py

@@ -45,35 +45,13 @@ def process_input(text, image=None):
         inputs = processor(prompt, return_tensors="pt").to(model.device)
 
     # Generate output from the model
-    outputs = model.generate(**inputs, max_new_tokens=100)
+    outputs = model.generate(**inputs, max_new_tokens=50)
 
     # Decode the output to return a readable text
     decoded_output = processor.decode(outputs[0], skip_special_tokens=True)
 
     return decoded_output
 
-# Gradio Interface Setup
-# def demo():
-#     # Define Gradio input and output components
-#     text_input = gr.Textbox(label="Text Input", placeholder="Enter text here", lines=5)
-
-#     # Use type="pil" to work with PIL Image objects
-#     image_input = gr.Image(label="Upload an Image", type="pil")
-
-#     output = gr.Textbox(label="Model Output", lines=5)
-
-#     # Define the interface layout
-#     interface = gr.Interface(
-#         fn=process_input,
-#         inputs=[text_input, image_input],
-#         outputs=output,
-#         title="Llama 3.2 Multimodal Text-Image Analyzer",
-#         description="Upload an image and/or provide text for analysis using the Llama 3.2 Vision Model."
-#     )
-
-#     # Launch the demo
-#     interface.launch()
-
 def demo():
     # Define Gradio input and output components
     text_input = gr.Textbox(label="Text Input", placeholder="Enter text here", lines=5)