ValueError: Error raised by inference API: Model tiiuae/falcon-40b-instruct time out using HuggingFaceHub

#55
by nicoleds - opened

I got this error "ValueError: Error raised by inference API: Model tiiuae/falcon-40b-instruct time out" using the code below (The same code works when using tiiuae/falcon-7b-instruct):

from langchain import PromptTemplate, HuggingFaceHub, LLMChain

template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate(template=template, input_variables=["question"])

llm_chain = LLMChain(prompt=prompt,
llm=HuggingFaceHub(repo_id="tiiuae/falcon-40b-instruct",
model_kwargs={"temperature":0.1,
"max_length":1000}))

question = "What is the capital of China?"

print(llm_chain.run(question))

Any idea why?

On the main page it says:

"Hosted inference API
Text Generation
Inference API has been turned off for this model."

Sign up or log in to comment