Update app.py

app.py

@@ -17,7 +17,7 @@ def predict_answer(image, question):
     # Prepare inputs
     encoding = processor(image, question, return_tensors="pt")
 
-    out = model.generate(**encoding)
+    out = model.generate(**encoding, max_length=512)
     generated_text = processor.decode(out[0], skip_special_tokens=True)
 
     return generated_text
@@ -33,7 +33,7 @@ iface = gr.Interface(
     inputs=[gr.Image(type="pil", label="Upload or Drag an Image"), gr.Textbox(label="Question", placeholder="e.g. What is this?", scale=4)],
     outputs=gr.TextArea(label="Answer"),
     title="Visual Question Answering",
-    description="This model answers questions based on the content of an image. Powered by BLIP.",
+    description="Tiny 1B parameter Vision Language Model.",
 )
 
 # Launch the app