nomic-ai/modernbert-embed-base
Primitive: /encode · Encode ·
ModernBERT
ModernBERT Embed is an embedding model trained from ModernBERT-base, bringing the new advances of ModernBERT to embeddings!
Long contextDense
View on Hugging Face → Fine-tuned from answerdotai/ModernBERT-base
Overview
Hardware: — drives latency, throughput & cost
| Size | 149M params |
|---|---|
| Tasks | /encode |
| 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.
Embedding
| Output types | Dense |
|---|---|
| Dimensions | dense: 768 |
| Max sequence length | 8,192 |
| Inputs | text |
Benchmarks
CQADupstackPhysicsRetrieval
Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.4479
map at 10 0.3889
mrr at 10 0.4444
FiQA2018
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.4073
map at 10 0.3289
mrr at 10 0.4936
NFCorpus
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3337
map at 10 0.1219
mrr at 10 0.5311
SCIDOCS
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.1855
map at 10 0.1100
mrr at 10 0.3229
SciFact
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.6968
map at 10 0.6479
mrr at 10 0.6625
Compare (0)Compare →