This model is a
77.96% smaller
version of
ibm-granite/granite-embedding-107m-multilingual
optimized for
German
language via vocabulary size reduction using the
trimming
method.
This trimmed model should perform similarly to the original model with only 32,768 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-deu-32768")
# Run inference with queries and documents
query = "My query in German"
documents = [
"Chunk in German",
"Chunk in German",
"Chunk in German",
]
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-deu-32768 on huggingface.co
104
Total runs
16
24-hour runs
21
3-day runs
22
7-day runs
27
30-day runs
More Information About granite-embedding-107m-deu-32768 huggingface.co Model
More granite-embedding-107m-deu-32768 license Visit here:
granite-embedding-107m-deu-32768 huggingface.co is an AI model on huggingface.co that provides granite-embedding-107m-deu-32768's model effect (), which can be used instantly with this alphaedge-ai granite-embedding-107m-deu-32768 model. huggingface.co supports a free trial of the granite-embedding-107m-deu-32768 model, and also provides paid use of the granite-embedding-107m-deu-32768. Support call granite-embedding-107m-deu-32768 model through api, including Node.js, Python, http.
granite-embedding-107m-deu-32768 huggingface.co is an online trial and call api platform, which integrates granite-embedding-107m-deu-32768's modeling effects, including api services, and provides a free online trial of granite-embedding-107m-deu-32768, you can try granite-embedding-107m-deu-32768 online for free by clicking the link below.
alphaedge-ai granite-embedding-107m-deu-32768 online free url in huggingface.co:
granite-embedding-107m-deu-32768 is an open source model from GitHub that offers a free installation service, and any user can find granite-embedding-107m-deu-32768 on GitHub to install. At the same time, huggingface.co provides the effect of granite-embedding-107m-deu-32768 install, users can directly use granite-embedding-107m-deu-32768 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
granite-embedding-107m-deu-32768 install url in huggingface.co: