urchade/gliner_large-v2.1
Primitive: /extract · Extract ·
DeBERTa
GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoder (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite th...
MultilingualEntities
Overview
Hardware: — drives latency, throughput & cost
| Size | 435M params |
|---|---|
| Tasks | /extract |
| License | apache-2.0 |
| Languages | multilingual |
| Latency | 175 ms |
| Throughput | 5.9K tok/s |
| Cost | $0.037 /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 | — |
Benchmarks
CoNLL-2003
Named entity recognition on Reuters newswire text
Corpus: 3,453 Queries: 3,453
Quality
f1 0.5483
precision 0.4747
recall 0.6487
Performance L4 b1 c16
Compare (0)Compare →