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

prithivida/Splade_PP_en_v2

Trained by Donkey Stereotype

Overview

Architecture
BERT
Parameters
110M
Tasks
Encode
Outputs
Sparse
Dimensions
Sparse: 30,522
Max Sequence Length
128 tokens
License
apache-2.0
Languages
en

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Performance L4 b1 c16
Corpus 36.1K tok/s
Corpus p50 53.3ms
Query 3.5K tok/s
Query p50 48.4ms
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Performance L4 b1 c16
Corpus 15.6K tok/s
Corpus p50 54.1ms
Query 1.8K tok/s
Query p50 48.1ms
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Performance L4 b1 c16
Corpus 41.4K tok/s
Corpus p50 56.1ms
Query 3.4K tok/s
Query p50 52.4ms
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Performance L4 b1 c16
Corpus 122.4K tok/s
Corpus p50 54.9ms
Query 5.4K tok/s
Query p50 47.5ms
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3161
map at 10 0.1188
mrr at 10 0.5185
Performance L4 b1 c16
Corpus 71.6K tok/s
Corpus p50 60.5ms
Query 1.4K tok/s
Query p50 54.1ms
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Performance L4 b1 c16
Corpus 49.8K tok/s
Corpus p50 55.8ms
Query 3.7K tok/s
Query p50 47.4ms
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Performance L4 b1 c16
Corpus 68.5K tok/s
Corpus p50 56.9ms
Query 5.0K tok/s
Query p50 52.2ms
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Performance L4 b1 c16
Corpus 65.1K tok/s
Corpus p50 53.6ms
Query 84.7K tok/s
Query p50 54.7ms
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 2.1K

Contact us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.