加载中…
加载中…
This model is a 70.91% smaller version of intfloat/multilingual-e5-small optimized for Gujarati 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.
| Metric | Original | Trimmed | Reduction |
|---|---|---|---|
| Vocabulary size | 250,037 tokens | 32,768 tokens | 86.89% |
| Model size | 117,653,760 params | 34,222,464 params | 70.91% |
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("alphaedge-ai/multilingual-e5-small-guj-32768")
# Run inference with queries and documents
query = "My query in Gujarati"
documents = [
"Chunk in Gujarati",
"Chunk in Gujarati",
"Chunk in Gujarati",
]
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)
@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}
}
@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},
}