Getting the following error when running load_qa_chain with map_reduce:
Token indices sequence length is longer than the specified maximum sequence length for this model (2108 > 1024
The code:
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model="ehartford/WizardLM-7B-Uncensored"
text_gen_pipeline = pipeline(
model = model,
model_kwargs= {
"device_map": "auto",
"load_in_8bit": True,
# default-explain-code settings from https://platform.openai.com/examples
"temperature": 0,
"top_p": 1.0,
},
max_new_tokens=2500)
from langchain import HuggingFacePipeline
llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
from langchain.text_splitter import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(
chunk_size = 1000,
chunk_overlap = 50)
# data is loaded with GitLoader
chunks = text_splitter.split_documents(data)
from langchain.embeddings import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings()
from langchain.vectorstores.faiss import FAISS
vectorstore = FAISS.from_documents(chunks, embeddings)
query = "How do you use the HamburgerMenu component?"
docs = vectorstore.similarity_search(query)
from langchain.chains.question_answering import load_qa_chain
chain = load_qa_chain(llm, chain_type="stuff")
result = chain.run(input_documents=docs, question=query)
