granite-embedding-107m-nld-16384

This model is a 83.84% smaller version of ibm-granite/granite-embedding-107m-multilingual optimized for Dutch 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.

Model Statistics

Metric Original Trimmed Reduction
Vocabulary size 250,002 tokens 16,384 tokens 93.45%
Model size 106,994,304 params 17,284,992 params 83.84%

image

Mining Dataset Statistics

Usage

from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("alphaedge-ai/granite-embedding-107m-nld-16384")
# Run inference with queries and documents
query = "My query in Dutch"
documents = [
    "Chunk in Dutch",
    "Chunk in Dutch",
    "Chunk in Dutch",
]
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}, 
}
Downloads last month
6
Safetensors
Model size
17.3M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for alphaedge-ai/granite-embedding-107m-nld-16384

Quantized
(36)
this model

Dataset used to train alphaedge-ai/granite-embedding-107m-nld-16384

Collection including alphaedge-ai/granite-embedding-107m-nld-16384

Paper for alphaedge-ai/granite-embedding-107m-nld-16384