TheBloke

/

Mistral-7B-Instruct-v0.2-AWQ

like 41

Hi there,

I'm getting this error when I try to pass the model to the llm parameter in langchain's RetrievalQASourceChain parameter, Below is my code.

def __init__(self, **kwargs):
        """
        Initializes the QA bot with a Qdrant client, embeddings, and a language model.

        Parameters:
        - **kwargs: Additional keyword arguments for configuration.
        """
        
        self.client = QdrantClient(url=HOST_NAME,api_key=API_KEY)
        self.embedding = get_embedding()
        self.device = "cuda:0" 
        if torch.cuda.is_available():
            print("Inside GPU")
            
            self.llm = AutoModelForCausalLM.from_pretrained(
                                HF_MODEL,
                                low_cpu_mem_usage=True,
                                device_map=self.device
                            )
        else:
            self.llm = CTransformers(model=MODEL_PATH,
                                    model_type=MODEL_TYPE, 
                                    config=MODEL_PARAMETERS)


def answer(query):
qa = RetrievalQAWithSourcesChain.from_chain_type(
                                llm=self.llm,
                                retriever=retriever,
                                chain_type_kwargs={
                                    "prompt": my_prompt
                                },
                                device_map=self.device,
                                reduce_k_below_max_tokens=True,
                                return_source_documents=True)
        

These are methods of a class that I have shared partial code here. Thanks for your understanding.

Error Message:

Traceback (most recent call last):
  File "/home/manoranjan.n/doc_test/backend/main.py", line 68, in ask_model
    result = qabot.answer(data['question'])
  File "/home/manoranjan.n/doc_test/backend/qa_bot.py", line 227, in answer
    qa = RetrievalQAWithSourcesChain.from_chain_type(
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain/chains/qa_with_sources/base.py", line 85, in from_chain_type
    combine_documents_chain = load_qa_with_sources_chain(
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain/chains/qa_with_sources/loading.py", line 183, in load_qa_with_sources_chain
    return _func(llm, verbose=verbose, **kwargs)
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain/chains/qa_with_sources/loading.py", line 62, in _load_stuff_chain
    llm_chain = LLMChain(llm=llm, prompt=prompt, verbose=verbose)
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain_core/load/serializable.py", line 107, in __init__
    super().__init__(**kwargs)
  File "pydantic/main.py", line 341, in pydantic.main.BaseModel.__init__
pydantic.error_wrappers.ValidationError: 2 validation errors for LLMChain
llm
  instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)
llm
  instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)

Somekind of validation error, please help me on this.