System prompt

app.py

@@ -68,14 +68,12 @@ def chat_llama3_8b(message: str,
         str: The generated response.
     """
     conversation = [{"role": "system", "content": system_prompt}]
-    conversation = []
     for user, assistant in history:
         conversation.append({"role": "user", "content": user})
         conversation.append({"role": "assistant", "content": assistant})
 
     conversation.append({"role": "user", "content": message})
 
-
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
     attention_mask = input_ids.ne(tokenizer.pad_token_id).long()