vidore/colqwen2.5-v0.2

Architecture

Qwen2

Parameters

7.0B

Tasks

Encode

Outputs

Multi-Vec

Dimensions

Multi-Vec: 128

Max Sequence Length

2,048 tokens

License

—

View on HuggingFace →

Benchmarks

Vidore3ComputerScienceRetrieval

technology retrieval en

Quality

ndcg at 10 0.7680

map at 10 0.6543

mrr at 10 0.8726

Performance L4 b1 c4

Corpus TPS 2

Corpus p50 1.9s

Query TPS 139

Query p50 527.1ms

Vidore3FinanceEnRetrieval

finance retrieval en

Quality

ndcg at 10 0.6207

map at 10 0.5008

mrr at 10 0.7416

Performance L4 b1 c4

Corpus TPS 2

Corpus p50 1.9s

Query TPS 150

Query p50 547.2ms

Vidore3HrRetrieval

general retrieval en

Quality

ndcg at 10 0.6034

map at 10 0.4666

mrr at 10 0.7046

Performance L4 b1 c4

Corpus TPS 2

Corpus p50 2.0s

Query TPS 110

Query p50 769.7ms

Vidore3PharmaceuticalsRetrieval

medical retrieval en

Quality

ndcg at 10 0.6274

map at 10 0.5173

mrr at 10 0.7234

Performance L4 b1 c4

Corpus TPS 2

Corpus p50 1.9s

Query TPS 138

Query p50 565.3ms

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.