Nick Yeo

Fixing this wouldn't solve the issue for Llama 2 template or ChatML template. It requires more than a prefix, but the ability to add a suffix as well. I believe...

My use case was that I was trying to use LLMChain with ChatPromptTemplate and ConversationBufferMemory like so: ``` prompt = ChatPromptTemplate.from_messages([ SystemMessage(content="You are a helpful AI assistant that gives concise...