This model is a 39.73% smaller version of intfloat/multilingual-e5-large-instruct optimized for French 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.

Model Statistics

Metric	Original	Trimmed	Reduction
Vocabulary size	250,002 tokens	32,768 tokens	86.89%
Model size	559,890,432 params	337,442,816 params	39.73%

Mining Dataset Statistics

Number of texts used for mining: 200,000 texts
Dataset: Lumberjackk/fineweb-2-trimming

Usage

python

from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("Lumberjackk/multilingual-e5-large-instruct-pms-32768")
# Run inference with queries and documents
query = "My query"
documents = [
    "Chunk 1",
    "Chunk 2",
    "Chunk 3",
]
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)

Citation

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}
}

alphaedge-ai/multilingual-e5-large-instruct-pms-32768

multilingual-e5-large-instruct-['pms']-32768

Model Statistics

Mining Dataset Statistics

Usage

Citation

Multilingual E5

alphaedge-ai/
multilingual-e5-large-instruct-pms-32768