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

← Catalog

jackboyla/glirel-large-v0

Open comparison →

Primitive: /extract · Extract · DeBERTa

GLiREL is a Relation Extraction model capable of classifying unseen relations given the entities within a text. This builds upon the excelent work done by Urchade Zaratiana, Nadi Tomeh, Pierre Holat, Thierry Charnois on the GLiNER library which enables efficient zero-shot Named Entity Recognition.

Relations

Overview

Hardware: — drives latency, throughput & cost

Size435M params
Tasks /extract
License
Latency105 ms
Throughput7.3K tok/s
Cost$0.030 /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Extraction

Output kindsRelations
Inputstext
Max sequence length

Benchmarks

FewRel

general re en

Few-shot relation extraction from Wikipedia sentences

Corpus: 70,000 Queries: 70,000
Quality
f1 0.2639
precision 0.2397
recall 0.2934
Performance L4-SPOT b1 c16
Performance L4 b1 c16
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.