I was implementing RAG on a document with using the LLama2 model but my model is asking questions to itself and answering it to them. llm = LlamaCpp(model_path=model_path, temperature=0, max_tokens=2000, top_p=0.1, n_ctx=2048, ) qa_chain = ConversationalRetrievalChain.from_llm( llm, vectorstore.as_retriever(search_kwargs={'k': 2}), ) chat_history = [] while True: query = input('Prompt: ') if query.lower() in ["exit", "quit", "q"]:...
Originally asked by Knox on Stack Exchange (stackoverflow) (CC BY-SA 4.0).
