knowledgator/gliner-bi-base-v2.0
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
View on Hugging Face → Fine-tuned from jhu-clsp/ettin-encoder-32m
Overview
Hardware: — drives latency, throughput & cost
| Size | null params |
|---|---|
| Tasks | /extract |
| License | apache-2.0 |
| Languages | en |
| Latency | 133 ms |
| Throughput | 7.1K 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 kinds | Entities |
|---|---|
| Inputs | text |
| Max sequence length | 1,024 |
Benchmarks
CoNLL-2003
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
Compare (0)Compare →