max limit set to 1024

app.py

@@ -66,7 +66,7 @@ def predict_text(text):
     # inputs = processor(image, input_text, return_tensors="pt").to(device)
     inputs = processor(text=text, return_tensors="pt").to("cuda")
     # Generate a response from the model
-    outputs = model.generate(**inputs, max_new_tokens=250)
+    outputs = model.generate(**inputs, max_new_tokens=1024)
     
     # Decode the output to return the final response
     response = processor.decode(outputs[0], skip_special_tokens=True)