cross-encoder/ms-marco-MiniLM-L-12-v2
Primitive: /score · Score ·
BERT
This model was trained on the MS Marco Passage Ranking task.
View on Hugging Face → Fine-tuned from microsoft/MiniLM-L12-H384-uncased
Overview
Hardware: — drives latency, throughput & cost
| Size | 33M params |
|---|---|
| Tasks | /score |
| License | apache-2.0 |
| Languages | en |
| Latency | 40 ms |
| Throughput | 26.4K tok/s |
| Cost | $0.0084 /1M tok |
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Scoring
| Inputs | text |
|---|---|
| Max sequence length | 512 |
Benchmarks
AskUbuntuDupQuestions
Duplicate question detection from AskUbuntu
Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6145
map at 10 0.4558
mrr at 10 0.6921
Performance L4 b1 c16
Query 8.2K tok/s
Query p50 31.7ms
CMedQAv1Reranking
Chinese medical question answering reranking (v1)
Corpus: 100,000 Queries: 2,000
Quality
map at 10 0.1016
mrr at 10 0.1528
CMedQAv2Reranking
Chinese medical question answering reranking (v2)
Corpus: 108,000 Queries: 4,000
Quality
map at 10 0.1218
mrr at 10 0.1812
MMarcoReranking
Multilingual MARCO passage reranking (Chinese)
Quality
map at 10 0.0426
mrr at 10 0.0446
Performance L4 b1 c16
Compare (0)Compare →