Why did we open-source our inference engine? Read the post

BAAI/bge-reranker-base

Architecture
Parameters
278M
Tasks
Score
Outputs
Score
Max Sequence Length
512 tokens
License

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Quality
ndcg at 10 0.5926
map at 10 0.4326
mrr at 10 0.6741
Performance L4 b1 c16
Query TPS 5.0K
Query p50 33.2ms

CMedQAv1Reranking

medical reranking zh

Quality
map at 10 0.8073
mrr at 10 0.8414

CMedQAv2Reranking

medical reranking zh

Quality
map at 10 0.8358
mrr at 10 0.8679

MMarcoReranking

general reranking zh

Quality
map at 10 0.3422
mrr at 10 0.3460
Performance L4 b1 c16

T2Reranking

general reranking zh

Quality
map at 10 0.5590
mrr at 10 0.7716

Self-hosted inference for search & document processing

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.

Github
1.5K

Contact us

Tell us about your use case and we'll get back to you shortly.