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

← Catalog

knowledgator/gliner-bi-base-v2.0

Open comparison →

Primitive: /extract · Extract ·

GLiNER-bi-Encoder is a novel architecture for Named Entity Recognition (NER) that combines zero-shot flexibility with industrial-scale efficiency. Unlike the original GLiNER, which uses joint encoding, the bi-encoder design decouples text and entity-type encoding, enabling the recognition of thou...

Entities

Overview

Hardware: — drives latency, throughput & cost

Sizenull params
Tasks /extract
Licenseapache-2.0
Languagesen
Latency133 ms
Throughput7.1K tok/s
Cost$0.031 /1M tok

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

Extraction

Output kindsEntities
Inputstext
Max sequence length1,024

Benchmarks

CoNLL-2003

news ner en

Named entity recognition on Reuters newswire text

Corpus: 3,453 Queries: 3,453
Quality
f1 0.6396
precision 0.5844
recall 0.7064
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 2.3K

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.