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

Alibaba-NLP/gte-reranker-modernbert-base

We are excited to introduce the `gte-modernbert` series of models, which are built upon the latest modernBERT pre-trained encoder-only foundation models. The `gte-modernbert` series models include both text embedding models and rerank models.

Architecture
ModernBERT
Parameters
150M
Tasks
Score
Outputs
Score
Max Sequence Length
8,192 tokens
License
apache-2.0
Languages
en

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6701
map at 10 0.5148
mrr at 10 0.7570
Performance L4 b1 c16
Query TPS 6.2K
Query p50 41.9ms
Reference →

CMedQAv1Reranking

medical reranking zh

Chinese medical question answering reranking (v1)

Corpus: 100,000 Queries: 2,000
Quality
map at 10 0.4989
mrr at 10 0.5905
Reference →

CMedQAv2Reranking

medical reranking zh

Chinese medical question answering reranking (v2)

Corpus: 108,000 Queries: 4,000
Quality
map at 10 0.5024
mrr at 10 0.5880
Reference →

MMarcoReranking

general reranking zh

Multilingual MARCO passage reranking (Chinese)

Quality
map at 10 0.2271
mrr at 10 0.2373
Performance L4 b1 c16
Reference →

T2Reranking

general reranking zh

Chinese passage ranking benchmark

Quality
map at 10 0.5537
mrr at 10 0.7882
Reference →

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.