jinaai/jina-colbert-v2 (Score)

Trained by Jina AI.

Architecture

XLM-RoBERTa

Parameters

559M

Tasks

Encode

Outputs

Multi-Vec

Dimensions

Multi-Vec: 128

Max Sequence Length

8,192 tokens

License

cc-by-nc-4.0

Languages

multilingual, af, am, ar, as, az, be, bg, bn, br, bs, ca, cs, cy, da, de, el, en, eo, es, et, eu, fa, fi, fr, fy, ga, gd, gl, gu, ha, he, hi, hr, hu, hy, id, is, it, ja, jv, ka, kk, km, kn, ko, ku, ky, la, lo, lt, lv, mg, mk, ml, mn, mr, ms, my, ne, nl, no, om, or, pa, pl, ps, pt, ro, ru, sa, sd, si, sk, sl, so, sq, sr, su, sv, sw, ta, te, th, tl, tr, ug, uk, ur, uz, vi, xh, yi, zh

View on HuggingFace →

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039

Performance L4-SPOT b1 c16

Corpus 3.3K tok/s

Corpus p50 325.6ms

Query 163 tok/s

Query p50 490.5ms

Performance L4 b1 c16

Corpus 22.9K tok/s

Corpus p50 83.9ms

Query 2.9K tok/s

Query p50 59.2ms

Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500

Performance L4-SPOT b1 c16

Corpus 798 tok/s

Corpus p50 555.8ms

Query 127 tok/s

Query p50 364.0ms

Performance L4 b1 c16

Corpus 13.4K tok/s

Corpus p50 65.7ms

Query 1.6K tok/s

Query p50 60.4ms

Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648

Performance L4-SPOT b1 c16

Corpus 1.7K tok/s

Corpus p50 656.4ms

Query 218 tok/s

Query p50 412.6ms

Performance L4 b1 c16

Corpus 25.8K tok/s

Corpus p50 95.6ms

Query 3.0K tok/s

Query p50 60.7ms

Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396

Performance L4-SPOT b1 c16

Corpus 5.8K tok/s

Corpus p50 568.2ms

Query 216 tok/s

Query p50 517.1ms

Performance L4 b1 c16

Corpus 27.5K tok/s

Corpus p50 274.0ms

Query 3.1K tok/s

Query p50 74.2ms

Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323

Performance L4-SPOT b1 c16

Corpus 3.0K tok/s

Corpus p50 622.8ms

Query 77 tok/s

Query p50 440.1ms

Performance L4 b1 c16

Corpus 30.3K tok/s

Corpus p50 156.2ms

Query 1.2K tok/s

Query p50 63.6ms

Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000

Performance L4-SPOT b1 c16

Corpus 2.8K tok/s

Corpus p50 521.5ms

Query 165 tok/s

Query p50 520.0ms

Performance L4 b1 c16

Corpus 26.7K tok/s

Corpus p50 108.8ms

Query 2.7K tok/s

Query p50 62.0ms

Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300

Performance L4-SPOT b1 c16

Corpus 4.6K tok/s

Corpus p50 397.7ms

Query 269 tok/s

Query p50 436.5ms

Performance L4 b1 c16

Corpus 29.3K tok/s

Corpus p50 145.2ms

Query 3.9K tok/s

Query p50 65.2ms

Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994

Performance L4-SPOT b1 c16

Corpus 3.4K tok/s

Corpus p50 554.5ms

Query 3.9K tok/s

Query p50 505.2ms

Performance L4 b1 c16

Corpus 19.2K tok/s

Corpus p50 162.2ms

Query 40.0K tok/s

Query p50 88.2ms

Reference →

Benchmarks

CQADupstackPhysicsRetrieval

CosQA

FiQA2018

LegalBenchConsumerContractsQA

NFCorpus

SCIDOCS

SciFact

StackOverflowQA

Self-hosted inference for search & document processing