The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models
Paper • 2101.05667 • Published
How to use castorini/duot5-base-msmarco with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("castorini/duot5-base-msmarco")
model = AutoModelForSeq2SeqLM.from_pretrained("castorini/duot5-base-msmarco")YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This model is a T5-base pairwise reranker fine-tuned on MS MARCO passage dataset for 50k steps (or 5 epochs).
For more details on how to use it, check pygaggle.ai
Paper describing the model: The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models