Update app.py

app.py

@@ -22,7 +22,7 @@ def generate_response(passage: str, question: str) -> str:
     inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
     response = model.generate(input_ids=inputs.to(model.device), max_new_tokens=100)
     
-    response = tokenizer.batch_decode(response, skip_special_tokens=True)[0]
+    response = tokenizer.batch_decode(response, skip_special_tokens=True)[0].split("<|assistant|>")[-1].strip()
     
     
     return response