cross-encoder/nli-deberta-v3-base
Primitive: /extract · Extract ·
DeBERTa
This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-base
View on Hugging Face → Fine-tuned from microsoft/deberta-v3-base
Overview
Hardware: — drives latency, throughput & cost
| Size | 184M params |
|---|---|
| Tasks | /extract |
| License | apache-2.0 |
| Languages | en |
| 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 | Class Labels |
|---|---|
| Inputs | text |
| Max sequence length | 512 |
Benchmarks
AG News
Topic classification of news articles into world, sports, business, and sci/tech categories
Corpus: 7,600 Queries: 7,600
Quality
accuracy 0.6497
medical_questions_pairs
Classify whether two medical questions ask the same thing (question-pair similarity)
Corpus: 3,048 Queries: 3,048
Quality
accuracy 0.5197
Compare (0)Compare →