fastino/gliner2-large-v1
Primitive: /extract · Extract ·
extractor
> Extract entities, classify text, parse structured data, and extract relations—all in one efficient model.
MultilingualEntities
Overview
Hardware: — drives latency, throughput & cost
| Size | 486M params |
|---|---|
| Tasks | /extract |
| License | apache-2.0 |
| Languages | en, fr, es |
| Latency | — |
| Throughput | — |
| Cost | — /1M tok |
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Extraction
| Output kinds | Entities |
|---|---|
| Inputs | text |
| Max sequence length | 512 |
Benchmarks
CoNLL-2003
Named entity recognition on Reuters newswire text
Corpus: 3,453 Queries: 3,453
Quality
f1 0.5401
precision 0.4564
recall 0.6613
Performance L4 b1 c16
FewRel
Few-shot relation extraction from Wikipedia sentences
Corpus: 70,000 Queries: 70,000
Quality
f1 0.4351
precision 0.8035
recall 0.2983
Performance L4 b1 c16
Compare (0)Compare →