Update app.py

app.py

@@ -20,7 +20,7 @@ def generate_response(passage: str, question: str) -> str:
     inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
     
     # Generate text, focusing only on the new tokens added by the model
-    outputs = model.generate(inputs.input_ids, max_new_tokens=150)
+    outputs = model.generate(**inputs, max_new_tokens=150)
     
     # Decode only the generated part, skipping the prompt input
     # generated_tokens = outputs[0][inputs.input_ids.shape[-1]:]  # Ignore input tokens in the output