使用 LLM Llama 3.1 8B 指导进行文本摘要

Question

我需要使用 LLM Llama 3.1 8B Instruct 进行抽象文本摘要。我的问题是如何一步步完成这个任务？我目前的程序是：

1. 加载 CNN Daily 数据集，用于具有特征（文章和摘要）的文本摘要
2. 在kaggle中加载本地磁盘中的模型和分词器
3. 使用Lora进行LLM参数训练
4. 使用分词器预处理数据集，用于带有输入提示的指导模型
5. 使用 TrainingArguments 和 SFTTrainer 进行训练

这是正确的程序还是我可以做得更好？

LLM参数训练的应用

Answer 1

我将提供一个代码片段，这将指导您如何构建自己的法学硕士。我建议你学习一些方法，例如 RAG-Rank、RAG-Fusion。

第一步是下载

ollama

，请遵循此链接，无论何时您想运行我在下面提供的Python类，始终确保应用程序正在运行。

import ollama
from operator import itemgetter
from langchain.retrievers.multi_query import MultiQueryRetriever
from langchain.prompts import ChatPromptTemplate, PromptTemplate
from langchain_community.vectorstores import FAISS
from langchain_core.output_parsers import StrOutputParser
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import UnstructuredPDFLoader
from ollama.embeddings import OllamaEmbeddings
from ollama import ChatOllama
from langchain.retrievers.multi_query import MultiQueryRetriever
from langchain_core.runnables import RunnablePassthrough


# Define a prompt for the RAG model
SYSTEM_PROMPT = """ You are very helpful assistant and also 
    an expert in summarizing documents,
    use all available resources to generate answers to the questions asked.
    You can return queries that you think are relevant to the question asked. \
    You will be asked to summarize a document here is the question: {question} \n
"""

def read_pdf_file(data):
    """
    Retrieve the data from the file

    Args: data: The data to be retrieved

    Returns: list: List of documents
    """

    local_path = "your_pdf_file_path"

    try:
       # Local PDF file uploads
       if local_path:
          loader = UnstructuredPDFLoader(file_path=local_path)
          data = loader.load()
       else:
          logging.error("Upload a PDF file")
    except Exception as e:
        raise  # Re-raise the exception to stop further execution

    # Split and chunk
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=7500, chunk_overlap=100)
    chunks = text_splitter.split_documents(data)

    try:
        ollama.embeddings(
            model="llama_3.1_8B_instruct",
            # prompt='Llamas are members of the camelid family',
        )
        embedding_model = (OllamaEmbeddings(model="llama_3.1_8B_instruct"),)
        vectorstore_db = FAISS.from_documents(
            documents=chunks, embedding=embedding_model
        )
        vectorstore_db.save_local("faiss_index")
        vector_retriever = vectorstore_db.as_retriever()

    except Exception as e:
        raise  # Re-raise the exception to stop further execution
    
    return vector_retriever

# RAG FUSION

    def main(self) -> str:
        """
        Implement the RAG fusion
        Args:
        question: The question to be answered

        Returns:
        str: The answer to the question
        """
        LLM_PROMPT = PromptTemplate(
        input_variables=["question"],
        template="""You are an AI language model assistant. Your task is to generate five
        summaries. Provide these alternative questions separated by newlines.
        Original question: {question}""",
       )
        template = """Answer the question based ONLY on the following context:
            {context}
            Question: {question}
            """
        prompt = ChatPromptTemplate.from_template(template)
        
        local_model = "llama_3.1_8B_instruct." #find the real name from ollama and download it
        llm = ChatOllama(model=local_model)
        retriever = read_pdf_file(self.data)
        retriever = MultiQueryRetriever.from_llm(
          retriever, llm, prompt=LLM_PROMPT 
        )

        chain = (
            {"context": retriever, "question": RunnablePassthrough()}
            | prompt
            | llm
            | StrOutputParser()
        )
        response = chain.invoke("summarize this documents about climate change")
        print(response)