Open BugApe opened 3 years ago
I would also love to know the answer to this.
Attached the evaluation script. It runs on the MSMARCO Top-1k passage re-ranking files: For each query, we have 1k passages given which need to be re-ranked
Amazing! Thanks for the quick response @nreimers !
And can you provide a eval code that reproduces these cross Encoder MRR@10 results on MS Marco Dev? https://sbert.net/docs/pretrained-models/ce-msmarco.html