This model is a 38.9% smaller version of
intfloat/multilingual-e5-large
for the French language, created using the
mtem-pruner space.
This pruned model should perform similarly to the original model for French language tasks with a much smaller
memory footprint. However, it may not perform well for other languages present in the original multilingual model as tokens not
commonly used in French were removed from the original multilingual model's vocabulary.
1from transformers import AutoModel, AutoTokenizer
2
3model_name = "antoinelouis/french-multilingual-e5-large"
4model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
5tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=True)
1from sentence_transformers import SentenceTransformer
2
3model = SentenceTransformer("antoinelouis/french-multilingual-e5-large")
