BeIR/sparta-msmarco-distilbert-base-v1
Feature Extraction
•
Updated
•
110
BEIR
university
Research interests
BEIR (Benchmarking IR) consists of a homogenous benchmark for diverse sentence or passage level IR tasks. It provides a common and easy framework for the cross-domain evaluation of your retrieval models.
Team members 2
datasets
49
BeIR/bioasq-generated-queries
Preview
•
Updated
•
5
BeIR/hotpotqa-generated-queries
Preview
•
Updated
•
5
BeIR/nq-generated-queries
Preview
•
Updated
•
22
BeIR/quora-generated-queries
Preview
•
Updated
•
5
BeIR/robust04-generated-queries
Preview
•
Updated
•
5
BeIR/cqadupstack-generated-queries
Preview
•
Updated
•
5
BeIR/signal1m-generated-queries
Preview
•
Updated
•
5
BeIR/webis-touche2020-generated-queries
Preview
•
Updated
•
6
BeIR/cqadupstack-qrels
Preview
•
Updated
•
4
BeIR/trec-news-generated-queries
Preview
•
Updated
•
5