Distilling Knowledge from Reader to Retriever for Question Answering
Paper β’ 2012.04584 β’ Published
How to use castorini/dkrr-dpr-nq-retriever with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="castorini/dkrr-dpr-nq-retriever") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("castorini/dkrr-dpr-nq-retriever")
model = AutoModel.from_pretrained("castorini/dkrr-dpr-nq-retriever")YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This model is converted from the original DKRR repo and ported into Pyserini:
@misc{izacard2020distilling,
title={Distilling Knowledge from Reader to Retriever for Question Answering},
author={Gautier Izacard and Edouard Grave},
year={2020},
eprint={2012.04584},
archivePrefix={arXiv},
primaryClass={cs.CL}
}