CoolFace
Modelpublic

alphaedge-ai/multilingual-e5-small-mri-16384

sourceHugging Facemitupdated 4mo agoView on Hugging Face
0likes86downloads
Model Card

multilingual-e5-small-mri-16384

This model is a 76.26% smaller version of intfloat/multilingual-e5-small optimized for Maori 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

MetricOriginalTrimmedReduction
Vocabulary size250,037 tokens16,384 tokens93.44%
Model size117,653,760 params27,931,008 params76.26%

image

Mining Dataset Statistics

Usage

python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("alphaedge-ai/multilingual-e5-small-mri-16384")
# Run inference with queries and documents
query = "My query in Maori"
documents = [
    "Chunk in Maori",
    "Chunk in Maori",
    "Chunk in Maori",
]
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

Multilingual E5
@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}
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}, 
}