google-flan-t5-inference.py

import os

import dotenv
from langchain import PromptTemplate, HuggingFaceHub, LLMChain

# Add your HuggingFace hub token in a `.env` file, as:
#
# ```
# HUGGINGFACEHUB_API_TOKEN=hf-....
# ```
dotenv.load_dotenv()

template = """Question: {question}

Answer: Let's think step by step."""
prompt = PromptTemplate(template=template, input_variables=["question"])

model_name = "google/flan-t5-xl"
llm=HuggingFaceHub(repo_id=model_name,
                   model_kwargs={"temperature":0, "max_length":128})

llm_chain = LLMChain(prompt=prompt, llm=llm)

question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"

# Don't even think for a second that the answer will be correct!
# F.ex.: Justin Bieber was born in 1994

print(llm_chain.run(question))