license: apache-2.0
language:
- en
pipeline_tag: sentence-similarity
library_name: sentence-transformers
tags:
- granite
- embeddings
- transformers
- mteb
Granite-Embedding-English-R2
Granite-Embedding-English-R2 is a 147M 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 768. 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.
The r2 models feature an increased context length of 8192 and deliver superior performance across standard and IBM-built information retrieval benchmarks (BEIR, UnifiedSearch, RedHAT, ClapNQ), code retrieval (COIR), and long-document search benchmarks (MLDR).
The Granite Embedding collection delivers innovative sentence-transformer models purposefully built for retrieval-based applications. These models use a bi-encoder architecture to generate high-quality embeddings from text inputs such as queries, passages, and documents, enabling seamless comparison through cosine similarity. Built using retrieval oriented pretraining, contrastive finetuning, knowledge distillation, and model merging, the Granite Embedding lineup is optimized to ensure strong alignment between query and passage embeddings.
The latest Granite Embedding r2 release introduces two English embedding models, both based on the ModernBERT architecture:
- granite-embedding-english-r2 (149M parameters): with an output embedding size of 768, replacing granite-embedding-125m-english.
- granite-embedding-small-english-r2 (47M parameters): A first-of-its-kind reduced-size model, with fewer layers and a smaller output embedding size (384), replacing granite-embedding-30m-english.
Model Details
Model Description
- Developed by: Granite Embedding Team, IBM
- Repository: ibm-granite/granite-embedding-models
- Paper [optional]: Technical Report
- Language(s) (NLP): English
- Release Date: July 31, 2024
- License: Apache 2.0
Uses
The model is designed to produce fixed length vector representations for a given text, which can be used for text similarity, retrieval, and search applications.
Usage with Sentence Transformers: The model is compatible with SentenceTransformer library and is very easy to use:
First, install the sentence transformers library
pip install sentence_transformers
The model can then be used to encode pairs of text and find the similarity between their representations
from sentence_transformers import SentenceTransformer, util
model_path = "ibm-granite/granite-embedding-english-r2"
# Load the Sentence Transformer model
model = SentenceTransformer(model_path)
input_queries = [
' Who made the song My achy breaky heart? ',
'summit define'
]
input_passages = [
"Achy Breaky Heart is a country song written by Don Von Tress. Originally titled Don't Tell My Heart and performed by The Marcy Brothers in 1991. ",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."
]
# encode queries and passages
query_embeddings = model.encode(input_queries)
passage_embeddings = model.encode(input_passages)
# calculate cosine similarity
print(util.cos_sim(query_embeddings, passage_embeddings))
Usage with Huggingface Transformers: This is a simple example of how to use the Granite-Embedding-278m-Multilingual model with the Transformers library and PyTorch.
First, install the required libraries
pip install transformers torch
The model can then be used to encode pairs of text
import torch
from transformers import AutoModel, AutoTokenizer
model_path = "ibm-granite/granite-embedding-english-r2"
# Load the model and tokenizer
model = AutoModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
model.eval()
input_queries = [
' Who made the song My achy breaky heart? ',
'summit define'
]
# tokenize inputs
tokenized_queries = tokenizer(input_queries, padding=True, truncation=True, return_tensors='pt')
# encode queries
with torch.no_grad():
# Queries
model_output = model(**tokenized_queries)
# Perform pooling. granite-embedding-278m-multilingual uses CLS Pooling
query_embeddings = model_output[0][:, 0]
# normalize the embeddings
query_embeddings = torch.nn.functional.normalize(query_embeddings, dim=1)
Evaluation Results
The performance of the Granite Embedding English models on MTEB Retrieval (i.e., BEIR) and code retrieval (CoIR) benchmarks is reported below. The average time required to encode and retrieve per query is also reported.
| Model | Parameters (M) | Embedding Size | MTEB-v1 Retrieval (15) | CoIR (10) | MLDR (En) | Retrieval Time (seconds/query) |
|---|---|---|---|---|---|---|
| granite-embedding-small-english-r2 | 47 | 384 | 50.8 | 53.8 | 39.8 | TBD |
| granite-embedding-english-r2 | 149 | 768 | 53.0 | 55.3 | 40.7 | TBD |
| granite-embedding-30m-english | 30 | 384 | 49.1 | 47.0 | 32.6 | TBD |
| granite-embedding-125m-englis | 125 | 768 | 52.3 | 50.3 | 35.0 | TBD |
Model Architecture and Key Features
The latest Granite Embedding r2 release introduces two English embedding models, both based on the ModernBERT architecture:
- granite-embedding-english-r2 (149M parameters): with an output embedding size of 768, replacing granite-embedding-125m-english.
- granite-embedding-small-english-r2 (47M parameters): A first-of-its-kind reduced-size model, with fewer layers and a smaller output embedding size (384), replacing granite-embedding-30m-english.
The following table shows the structure of the two models:
| Model | granite-embedding-small-english-r2 | granite-embedding-english-r2 |
|---|---|---|
| Embedding size | 384 | 768 |
| Number of layers | 12 | 22 |
| Number of attention heads | 12 | 12 |
| Intermediate size | 1536 | 1152 |
| Activation Function | GeGLU | GeGLU |
| Vocabulary Size | 50368 | 50368 |
| Max. Sequence Length | 8192 | 8192 |
| # Parameters | 47M | 149M |
Training and Optimization
The r2 models incorporate key enhancements from the ModernBERT architecture, including:
- Alternating attention lengths to accelerate processing
- Rotary position embeddings for extended sequence length
- A newly trained tokenizer optimized with code and text data
- Flash Attention 2.0 for improved efficiency
- Streamlined parameters, eliminating unnecessary bias terms
Data Collection
Granite embedding models are trained using data from four key sources:
- Unsupervised title-body paired data scraped from the web
- Publicly available paired with permissive, enterprise-friendly license
- IBM-internal paired data targetting specific technical domains
- IBM-generated synthetic data
Notably, we do not use the popular MS-MARCO retrieval dataset in our training corpus due to its non-commercial license (many open-source models use this dataset due to its high quality).
The underlying encoder models using GneissWeb, an IBM-curated dataset composed exclusively of open, commercial-friendly sources.
For governance, all our data undergoes a data clearance process subject to technical, business, and governance review. This comprehensive process captures critical information about the data, including but not limited to their content description ownership, intended use, data classification, licensing information, usage restrictions, how the data will be acquired, as well as an assessment of sensitive information (i.e, personal information).
Infrastructure
We train Granite Embedding Models using IBM's computing cluster, Cognitive Compute Cluster, which is outfitted with NVIDIA A100 80gb GPUs. This cluster provides a scalable and efficient infrastructure for training our models over multiple GPUs.
Ethical Considerations and Limitations
The data used to train the base language model was filtered to remove text containing hate, abuse, and profanity. Granite-Embedding-278m-Multilingual is finetuned on 12 languages, and has a context length of 512 tokens (longer texts will be truncated to this size).
Resources
- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
Citation
@misc{awasthy2025graniteembeddingmodels,
title={Granite Embedding Models},
author={Parul Awasthy and Aashka Trivedi and Yulong Li and Mihaela Bornea and David Cox and Abraham Daniels and Martin Franz and Gabe Goodhart and Bhavani Iyer and Vishwajeet Kumar and Luis Lastras and Scott McCarley and Rudra Murthy and Vignesh P and Sara Rosenthal and Salim Roukos and Jaydeep Sen and Sukriti Sharma and Avirup Sil and Kate Soule and Arafat Sultan and Radu Florian},
year={2025},
eprint={2502.20204},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2502.20204},
}