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

lightonai/Reason-ModernColBERT

Architecture
Parameters
305M
Tasks
Encode
Outputs
Multi-Vec
Dimensions
Multi-Vec: 128
Max Sequence Length
8,192 tokens
License

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Quality
ndcg at 10 0.4382
map at 10 0.3824
mrr at 10 0.4397
Performance L4 b1 c16
Corpus TPS 29.6K
Corpus p50 61.0ms
Query TPS 2.9K
Query p50 57.8ms

CosQA

technology retrieval en

Quality
ndcg at 10 0.3443
map at 10 0.2641
mrr at 10 0.2620
Performance L4 b1 c16
Corpus TPS 12.7K
Corpus p50 60.8ms
Query TPS 1.6K
Query p50 59.1ms

FiQA2018

finance retrieval en

Quality
ndcg at 10 0.4081
map at 10 0.3315
mrr at 10 0.4936
Performance L4 b1 c16
Corpus TPS 30.7K
Corpus p50 71.5ms
Query TPS 3.0K
Query p50 59.6ms

LegalBenchConsumerContractsQA

legal retrieval en

Quality
ndcg at 10 0.7777
map at 10 0.7287
mrr at 10 0.7307
Performance L4 b1 c16
Corpus TPS 50.0K
Corpus p50 144.2ms
Query TPS 4.2K
Query p50 60.7ms

NFCorpus

medical retrieval en

Quality
ndcg at 10 0.3580
map at 10 0.1342
mrr at 10 0.5702
Performance L4 b1 c16
Corpus TPS 44.6K
Corpus p50 89.2ms
Query TPS 1.4K
Query p50 56.3ms

SCIDOCS

scientific retrieval en

Quality
ndcg at 10 0.1710
map at 10 0.0986
mrr at 10 0.2991
Performance L4 b1 c16
Corpus TPS 27.0K
Corpus p50 80.8ms
Query TPS 2.8K
Query p50 60.8ms

SciFact

scientific retrieval en

Quality
ndcg at 10 0.7380
map at 10 0.6953
mrr at 10 0.7076
Performance L4 b1 c16
Corpus TPS 41.6K
Corpus p50 83.7ms
Query TPS 4.1K
Query p50 60.4ms

StackOverflowQA

technology retrieval en

Quality
ndcg at 10 0.5934
map at 10 0.5591
mrr at 10 0.5591
Performance L4 b1 c16
Corpus TPS 35.4K
Corpus p50 84.4ms
Query TPS 62.1K
Query p50 75.3ms

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.