Model Details
Full Model IDibm-granite/granite-embedding-small-english-r2
Pipeline / Taskfeature-extraction
Librarysentence-transformers
Downloads (all-time)5.9M
Likes111
Last Modified1/21/2026
Author / Orgibm-granite
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("feature-extraction", model="ibm-granite/granite-embedding-small-english-r2")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
sentence-transformerspytorchsafetensorsmodernbertfeature-extractiongraniteembeddingstransformersmtebenarxiv:2508.21085license:apache-2.0text-embeddings-inferenceendpoints_compatibledeploy:azureregion:us
More feature-extraction Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: feature-extraction
This model is designed for the feature-extraction task. Explore more models for this use case.
All feature-extraction Models →📊 Popularity
⬇ Downloads5.9M
❤️ Community Likes111
🛠️ Requirements
- →Install: pip install sentence-transformers
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.