LLMs感知世界
chatgpt、huggingchat等大模型逐渐进入人们的视野,这里总结一些可用的大模型,方便大家通过langchain、transformers直接使用:
from langchain import HuggingFaceHub
repo_id = "google/flan-t5-xl"
repo_id = "stabilityai/stablelm-tuned-alpha-3b"
repo_id = "databricks/dolly-v2-3b"
repo_id = "Writer/camel-5b-hf"
repo_id="gpt2"
llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature":0, "max_length":64})
将LLM作为controller,引导它去感知世界,为我们呈现真实的场景和体验。
from langchain.chains import LLMChain
template = """Question: {question}
Answer: Let's think step by step."""
prompt = PromptTemplate(template=template, input_variables=["question"])
llm_chain = LLMChain(prompt=prompt, llm=llm)
question= "Who won the FIFA World Cup in the year 1994? "
print(llm_chain.run(question)) # The FIFA World Cup is a football tournament that is played every 4 years. The year 1994 was the 44th FIFA World Cup. The final answer: Brazil.