ibm-granite/granite-embedding-small-english-r2
Primitive: /encode · Encode ·
ModernBERT
Model Summary: Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings.
Long contextDense
Overview
Hardware: — drives latency, throughput & cost
| Size | 48M 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: 384 |
| Max sequence length | 8,192 |
| Inputs | text |
Benchmarks
CosQA
Code search with natural language queries
Corpus: 6,267 Queries: 500
Quality
map at 10 0.2733
mrr at 10 0.3107
ndcg at 10 0.3530
FiQA2018
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
map at 10 0.2614
mrr at 10 0.3941
ndcg at 10 0.3317
NFCorpus
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3016
map at 10 0.1115
mrr at 10 0.5082
SCIDOCS
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Quality
map at 10 0.0595
mrr at 10 0.1655
ndcg at 10 0.1026
SciFact
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Quality
map at 10 0.6724
mrr at 10 0.6832
ndcg at 10 0.7157
StackOverflowQA
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Quality
map at 10 0.8818
mrr at 10 0.8818
ndcg at 10 0.9005
Compare (0)Compare →