Update app.py

app.py

@@ -86,12 +86,13 @@ Answer:"""
                     # Generate output
                     with torch.inference_mode():
                         output = model.generate(
-                            **inputs,
-                            max_new_tokens=256,
-                            do_sample=False,
-                            repetition_penalty=1.1
-                        )
-
+                        **inputs,
+                        max_new_tokens=512,  # increase if needed
+                        do_sample=False,
+                        repetition_penalty=1.1,
+                        eos_token_id=tokenizer.eos_token_id,
+                        pad_token_id=tokenizer.pad_token_id
+                    )
                     # Decode and clean output
                     decoded = tokenizer.decode(output[0], skip_special_tokens=True)
                     answer = decoded.split("Answer:")[-1].strip()