BeIR/cqadupstack
Viewer • Updated • 470k • 612
BEIR
university
AI & ML 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.
VORTEXRAG: 7-Layer RAG — EM 74.8 on QA benchmarks, solves Semantic Drift [open source]
1
#6 opened 3 months ago
by 
vigneshwar234
VORTEXRAG: 7-Layer RAG — EM 74.8 on QA benchmarks, solves Semantic Drift [open source]
1
#7 opened 3 months ago
by vigneshwar234
VORTEXRAG: 7-Layer RAG — EM 74.8 on QA benchmarks, solves Semantic Drift [open source]
1
#4 opened 3 months ago
by vigneshwar234
cqadupstack document collection
1
#3 opened about 1 year ago
by 
ftvalentini
nthakur
updated a
dataset 5 months ago
nthakur
published a
dataset 5 months ago
nthakur
updated a
dataset 5 months ago
Convert scifact dataset to Parquet
#3 opened 5 months ago
by 
nthakur
nthakur
updated a
dataset 5 months ago
Convert climate-fever dataset to Parquet
#3 opened 5 months ago
by nthakur
nthakur
updated a
dataset 5 months ago
Convert fever dataset to Parquet
#3 opened 5 months ago
by nthakur
nthakur
updated a
dataset 5 months ago
Convert scidocs dataset to Parquet
#3 opened 5 months ago
by nthakur
nthakur
updated a
dataset 5 months ago
Convert dbpedia-entity dataset to Parquet
#4 opened 5 months ago
by nthakur
nthakur
updated a
dataset 5 months ago
Convert quora dataset to Parquet
#4 opened 5 months ago
by nthakur
Convert quora dataset to Parquet
#5 opened 5 months ago
by nthakur
nthakur
updated a
dataset 5 months ago