from langchain.retrievers.document_compressors import CrossEncoderReranker
from langchain_community.cross_encoders import HuggingFaceCrossEncoder

model = HuggingFaceCrossEncoder(model_name="BAAI/bge-reranker-base")
compressor = CrossEncoderReranker(model=model, top_n=4)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)

Above is the code I am using for the reranking using HuggingFaceCrossEncoder. But I want to load this model in 16 bit instead of 32 bit. Is there any way I can load this model in 16 or 8 bit

model = HuggingFaceCrossEncoder(model_name="BAAI/bge-reranker-base",use_fp16=True)

I tried using above code but getting below error
ValidationError: 1 validation error for HuggingFaceCrossEncoder