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

ibm-granite/granite-embedding-30m-sparse

Model Summary: Granite-Embedding-30m-Sparse is a 30M parameter sparse biencoder embedding model from the Granite Experimental suite that can be used to generate high quality text embeddings.

Overview

Architecture
RoBERTa
Parameters
30M
Tasks
Encode
Outputs
Sparse
Dimensions
Sparse: 50,265
Max Sequence Length
512 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 22.8K tok/s
Corpus p50 94.5ms
Query 3.7K tok/s
Query p50 46.3ms
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Performance L4 b1 c16
Corpus 13.9K tok/s
Corpus p50 59.0ms
Query 2.1K tok/s
Query p50 45.2ms
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Performance L4 b1 c16
Corpus 25.0K tok/s
Corpus p50 106.9ms
Query 4.1K tok/s
Query p50 46.3ms
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Performance L4 b1 c16
Corpus 69.5K tok/s
Corpus p50 112.3ms
Query 5.7K tok/s
Query p50 46.7ms
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3147
map at 10 0.1224
mrr at 10 0.5112
Performance L4 b1 c16
Corpus 42.5K tok/s
Corpus p50 105.3ms
Query 1.0K tok/s
Query p50 51.6ms
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 30.3K tok/s
Corpus p50 103.1ms
Query 3.9K tok/s
Query p50 45.5ms
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Performance L4 b1 c16
Corpus 40.6K tok/s
Corpus p50 105.1ms
Query 5.9K tok/s
Query p50 45.7ms
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Performance L4 b1 c16
Corpus 33.6K tok/s
Corpus p50 109.4ms
Query 44.1K tok/s
Query p50 111.7ms
Reference →

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 2.0K

Contact us

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