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

NovaSearch/stella_en_400M_v5

Architecture
ModernBERT
Parameters
400M
Tasks
Encode
Outputs
Dense
Dimensions
Dense: 1,024
Max Sequence Length
512 tokens
License

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Quality
ndcg at 10 0.4836
map at 10 0.4156
mrr at 10 0.4717
Performance L4 b1 c16
Corpus TPS 24.3K
Corpus p50 84.2ms
Query TPS 2.5K
Query p50 56.9ms

CosQA

technology retrieval en

Quality
ndcg at 10 0.3216
map at 10 0.2529
mrr at 10 0.2719
Performance L4 b1 c16
Corpus TPS 12.8K
Corpus p50 67.0ms
Query TPS 1.4K
Query p50 59.0ms

FiQA2018

finance retrieval en

Quality
ndcg at 10 0.5589
map at 10 0.4742
mrr at 10 0.6391
Performance L4 b1 c16
Corpus TPS 24.7K
Corpus p50 97.7ms
Query TPS 2.6K
Query p50 59.9ms

LegalBenchConsumerContractsQA

legal retrieval en

Quality
ndcg at 10 0.8107
map at 10 0.7633
mrr at 10 0.7645
Performance L4 b1 c16
Corpus TPS 39.7K
Corpus p50 209.7ms
Query TPS 3.6K
Query p50 61.0ms

NFCorpus

medical retrieval en

Quality
ndcg at 10 0.4125
map at 10 0.1615
mrr at 10 0.6096
Performance L4 b1 c16
Corpus TPS 30.3K
Corpus p50 164.6ms
Query TPS 1.1K
Query p50 68.1ms

NanoFiQA2018Retrieval

finance retrieval en

Quality
ndcg at 10 0.6158
map at 10 0.5412
mrr at 10 0.6537
Performance L4 b1 c16
Corpus TPS 25.2K
Corpus p50 103.9ms
Query TPS 2.7K
Query p50 58.3ms

SCIDOCS

scientific retrieval en

Quality
ndcg at 10 0.2501
map at 10 0.1523
mrr at 10 0.4130
Performance L4 b1 c16
Corpus TPS 27.1K
Corpus p50 115.7ms
Query TPS 2.6K
Query p50 57.4ms

SciFact

scientific retrieval en

Quality
ndcg at 10 0.7842
map at 10 0.7358
mrr at 10 0.7455
Performance L4 b1 c16
Corpus TPS 28.4K
Corpus p50 156.1ms
Query TPS 3.4K
Query p50 60.0ms

StackOverflowQA

technology retrieval en

Quality
ndcg at 10 0.8666
map at 10 0.8439
mrr at 10 0.8439
Performance L4 b1 c16
Corpus TPS 28.2K
Corpus p50 134.6ms
Query TPS 31.9K
Query p50 153.3ms

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.