Update app.py

app.py

@@ -21,7 +21,7 @@ def infer_ocrvqa(image, question):
 
     inputs = processor(images=image,text=question, return_tensors="pt").to("cuda")
 
-    predictions = model.generate(**inputs, max_new_tokens=500)
+    predictions = model.generate(**inputs, max_new_tokens=200)
     
     return processor.decode(predictions[0], skip_special_tokens=True)[len(question):].lstrip("\n")