Update app.py

app.py

@@ -30,7 +30,7 @@ def predict(image, input_text):
     prompt_length = inputs['input_ids'].shape[1]
     
     # Generate
-    generate_ids = model.generate(**inputs, max_new_tokens=512)
+    generate_ids = model.generate(**inputs, num_beams=4, max_new_tokens=512)
     output_text = processor.batch_decode(generate_ids[:, prompt_length:], skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
 
     return output_text