Update app.py

app.py

@@ -81,7 +81,7 @@ def model_inference(
     inputs = inputs.to("cuda")
 
     # Inference: Generation of the output
-    generated_ids = model.generate(**inputs, max_new_tokens=128)
+    generated_ids = model.generate(**inputs, max_new_tokens=512)
     generated_ids_trimmed = [
         out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
     ]