Task
Feature Extraction
G
ibm-granite/granite-embedding-small-english-r2
Feature Extraction·ibm-granite· 2.2M· 73
sentence-transformers
apache-2.0
47.7M params
arxiv:2508.21085license:apache-2.0
feature extraction · sentence-transformers model
# pull & run locally
pip install mlforge-sdk && mlforge pull ibm-granite/granite-embedding-small-english-r2
pip install mlforge-sdk && mlforge pull ibm-granite/granite-embedding-small-english-r2
Model details
Provider
ibm-granite
Framework
sentence-transformers
Parameters
47.7M
License
apache-2.0
Downloads
2.2M
Likes
73
Paper
arXiv:2508.21085
Updated
2026-01-21
About ibm-granite/granite-embedding-small-english-r2
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. This model produces embedding vectors of size 384 based on context length of upto 8192 tokens. Compared to most other open-source models, this model was only trained using open-source relevance-pair datasets with permissive, enterprise-friendly license, plus IBM collected and generated datasets.