combining falcon 40b instruct with langchain

#87
by rra21 - opened

im want to build an llm where i can make it interact with my own data using langchain.

from langchain_community.llms import HuggingFaceHub

llm = HuggingFaceHub(
repo_id=model_name,
task="text-generation",
model_kwargs={
"max_new_tokens": 512,
"top_k": 30,
"temperature": 0.1,
"repetition_penalty": 1.03
},
huggingfacehub_api_token="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"
)

i reached the following stage yet when i run the following i get this error

from langchain_community.chat_models.huggingface import ChatHuggingFace
llm = ChatHuggingFace(llm=llm)

HfHubHTTPError: 401 Client Error: Unauthorized for url

and i am doing do this to be able to run the following:
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
retriever=vector_db.as_retriever()
)

what am i missing and is there a way to be able to do this fully local like doing the falcon model and pass it to ChatHuggingFace ?

thank you!

Sign up or log in to comment