This model is a
83.84% smaller
version of
ibm-granite/granite-embedding-107m-multilingual
optimized for
Arabic
language via vocabulary size reduction using the
trimming
method.
This trimmed model should perform similarly to the original model with only 16,384 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("alphaedge-ai/granite-embedding-107m-arb-16384")
# Run inference with queries and documents
query = "My query in Arabic"
documents = [
"Chunk in Arabic",
"Chunk in Arabic",
"Chunk in Arabic",
]
query_embeddings = model.encode_query(query)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# Compute similarities to determine a ranking
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
Citations
Granite Embedding Models
@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},
}
Trimming blog post
@misc{hf_blogpost_trimming,
title={Introduction to Trimming},
author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
year={2026},
url={https://huggingface.co/blog/lbourdois/introduction-to-trimming},
}
Runs of alphaedge-ai granite-embedding-107m-arb-16384 on huggingface.co
105
Total runs
3
24-hour runs
19
3-day runs
4
7-day runs
6
30-day runs
More Information About granite-embedding-107m-arb-16384 huggingface.co Model
More granite-embedding-107m-arb-16384 license Visit here:
granite-embedding-107m-arb-16384 huggingface.co is an AI model on huggingface.co that provides granite-embedding-107m-arb-16384's model effect (), which can be used instantly with this alphaedge-ai granite-embedding-107m-arb-16384 model. huggingface.co supports a free trial of the granite-embedding-107m-arb-16384 model, and also provides paid use of the granite-embedding-107m-arb-16384. Support call granite-embedding-107m-arb-16384 model through api, including Node.js, Python, http.
granite-embedding-107m-arb-16384 huggingface.co is an online trial and call api platform, which integrates granite-embedding-107m-arb-16384's modeling effects, including api services, and provides a free online trial of granite-embedding-107m-arb-16384, you can try granite-embedding-107m-arb-16384 online for free by clicking the link below.
alphaedge-ai granite-embedding-107m-arb-16384 online free url in huggingface.co:
granite-embedding-107m-arb-16384 is an open source model from GitHub that offers a free installation service, and any user can find granite-embedding-107m-arb-16384 on GitHub to install. At the same time, huggingface.co provides the effect of granite-embedding-107m-arb-16384 install, users can directly use granite-embedding-107m-arb-16384 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
granite-embedding-107m-arb-16384 install url in huggingface.co: