Ihor/gliner-biomed-large-v1.0
Primitive: /extract · Extract ·
DeBERTa
The model was presented in the paper GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity Recognition.
Entities
View on Hugging Face → Fine-tuned from microsoft/deberta-v3-large
Overview
Hardware: — drives latency, throughput & cost
| Size | 435M params |
|---|---|
| Tasks | /extract |
| License | apache-2.0 |
| Languages | en |
| Latency | 108 ms |
| Throughput | 9.9K tok/s |
| Cost | $0.023 /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 0.6439
precision 0.5903
recall 0.7082
Performance L4 b1 c16
Compare (0)Compare →