# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Luyu/bert-base-mdoc-hdct")
model = AutoModelForSequenceClassification.from_pretrained("Luyu/bert-base-mdoc-hdct")Quick Links
YAML Metadata Error:"datasets[0]" with value "MS MARCO document ranking" is not valid. If possible, use a dataset id from https://hf.co/datasets.
BERT Reranker for MS-MARCO Document Ranking
Model description
A text reranker trained for HDCT retriever on MS MARCO document dataset.
Intended uses & limitations
It is possible to work with other retrievers like BM25 but using aligned HDCT works the best.
How to use
See our project repo page.
Eval results
MRR @10: 0.434 on Dev. MRR @10: 0.382 on Eval.
BibTeX entry and citation info
@inproceedings{gao2021lce,
title={Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline},
author={Luyu Gao and Zhuyun Dai and Jamie Callan},
year={2021},
booktitle={The 43rd European Conference On Information Retrieval (ECIR)},
}
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Luyu/bert-base-mdoc-hdct")