Update app.py

app.py

@@ -19,7 +19,7 @@ input_ids = tokenizer.encode(query.lower(), return_tensors='pt').to(device)
 sample_outputs = model.generate(input_ids,
                                 do_sample=True,
                                 num_beams=1, 
-                                max_length=2560,
+                                max_length=4096,
                                 temperature=0.9,
                                 top_k = 30,
                                 num_return_sequences=1)