Update README.md

修改使用LangChain和HuggingFacePipeline本地调用HuggingFace模型的示例代码，原示例代码无法正确执行

Author: pengwork

README.md

@@ -845,25 +845,29 @@ print(llm_chain.run(question))
 将 Hugging Face 模型直接拉到本地使用
 
 ```python
+from langchain import PromptTemplate, LLMChain
 from langchain.llms import HuggingFacePipeline
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, AutoModelForSeq2SeqLM
 
 model_id = 'google/flan-t5-large'
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_id, load_in_8bit=True)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)  # load_in_8bit=True,  # , device_map='auto'
 
 pipe = pipeline(
     "text2text-generation",
-    model=model, 
-    tokenizer=tokenizer, 
+    model=model,
+    tokenizer=tokenizer,
     max_length=100
 )
 
 local_llm = HuggingFacePipeline(pipeline=pipe)
 print(local_llm('What is the capital of France? '))
 
 
-llm_chain = LLMChain(prompt=prompt,  llm=local_llm)
+template = """Question: {question} Answer: Let's think step by step."""
+prompt = PromptTemplate(template=template, input_variables=["question"])
+
+llm_chain = LLMChain(prompt=prompt, llm=local_llm)
 question = "What is the capital of England?"
 print(llm_chain.run(question))
 ```