Update llm.py

llm.py

@@ -8,13 +8,12 @@ def generate_answer(context, question):
 {context}
 
 Based on the above context, answer the question:
-Question: {question}
-Answer:"""
-
+{question}
+"""
     inputs = tokenizer(prompt, return_tensors='pt', truncation=True, max_length=512)
     outputs = model.generate(
         **inputs,
         max_new_tokens=80,
-        do_sample=False  # deterministic
+        do_sample=False
     )
     return tokenizer.decode(outputs[0], skip_special_tokens=True).strip()