Sentence Similarity
sentence-transformers
Safetensors
Transformers
French
English
bilingual
feature-extraction
sentence-embedding
mteb
custom_code
Eval Results (legacy)
Instructions to use Lajavaness/bilingual-embedding-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Lajavaness/bilingual-embedding-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Lajavaness/bilingual-embedding-large", trust_remote_code=True) sentences = [ "C'est une personne heureuse", "C'est un chien heureux", "C'est une personne très heureuse", "Aujourd'hui est une journée ensoleillée" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Lajavaness/bilingual-embedding-large with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Lajavaness/bilingual-embedding-large", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
finetuning
#2
by al-h - opened
Hello,
Thanks for the usefull and performing model ! I'd like to further finetune it on my data, could it be achieved by repeating your step 3 ? If so, what loss did you use and can it be done with sentence transformers ? If not can you advice how to do it?
Thanks in advance.
Hello @al-h
You can apply to finetune according to this article: https://lajavaness.medium.com/sentence-embedding-fine-tuning-for-the-french-language-65e20b724e88
Tuan