jinaai/jina-colbert-v2 (Encode)

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

Quality

ndcg at 10 0.4047

map at 10 0.3496

mrr at 10 0.4005

Performance L4 b1 c16

Corpus 24.9K tok/s

Corpus p50 81.3ms

Query 3.0K tok/s

Query p50 55.9ms

Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500

Quality

ndcg at 10 0.2607

map at 10 0.2037

mrr at 10 0.1946

Performance L4 b1 c16

Corpus 13.9K tok/s

Corpus p50 63.3ms

Query 1.5K tok/s

Query p50 59.7ms

Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648

Quality

ndcg at 10 0.4051

map at 10 0.3240

mrr at 10 0.4875

Performance L4 b1 c16

Corpus 27.1K tok/s

Corpus p50 93.4ms

Query 3.0K tok/s

Query p50 59.5ms

Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396

Quality

ndcg at 10 0.7615

map at 10 0.7107

mrr at 10 0.7116

Performance L4 b1 c16

Corpus 30.7K tok/s

Corpus p50 259.5ms

Query 3.4K tok/s

Query p50 60.1ms

Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323

Quality

ndcg at 10 0.3583

map at 10 0.1422

mrr at 10 0.5724

Performance L4 b1 c16

Corpus 33.2K tok/s

Corpus p50 146.1ms

Query 1.5K tok/s

Query p50 55.3ms

Reference →

NanoFiQA2018Retrieval

finance retrieval en

Smaller subset of the FiQA financial QA dataset

Quality

ndcg at 10 0.5208

map at 10 0.4318

mrr at 10 0.5644

Performance L4 b1 c16

Corpus 28.9K tok/s

Corpus p50 77.4ms

Query 2.6K tok/s

Query p50 49.5ms

Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000

Quality

ndcg at 10 0.1779

map at 10 0.1045

mrr at 10 0.3091

Performance L4 b1 c16

Corpus 28.5K tok/s

Corpus p50 105.7ms

Query 2.9K tok/s

Query p50 57.3ms

Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300

Quality

ndcg at 10 0.6702

map at 10 0.6266

mrr at 10 0.6391

Performance L4 b1 c16

Corpus 30.9K tok/s

Corpus p50 137.3ms

Query 4.8K tok/s

Query p50 56.4ms

Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994

Quality

ndcg at 10 0.6085

map at 10 0.5717

mrr at 10 0.5717

Performance L4 b1 c16

Corpus 27.4K tok/s

Corpus p50 127.2ms

Query 58.2K tok/s

Query p50 80.3ms

Reference →

Benchmarks

CQADupstackPhysicsRetrieval

CosQA

FiQA2018

LegalBenchConsumerContractsQA

NFCorpus

NanoFiQA2018Retrieval

SCIDOCS

SciFact

StackOverflowQA

Self-hosted inference for search & document processing