Feature Extraction
sentence-transformers
PyTorch
ONNX
Safetensors
OpenVINO
xlm-roberta
mteb
Sentence Transformers
sentence-similarity
Eval Results (legacy)
Eval Results
text-embeddings-inference
Instructions to use intfloat/multilingual-e5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use intfloat/multilingual-e5-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("intfloat/multilingual-e5-large") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Inference
- Notebooks
- Google Colab
- Kaggle
File Size
#24
by Eigenket27 - opened
It is mentioned that the model size is 2.24 GB but when i take a git pull the size goes to 13.54 GB, which files do i need to ignore while using for embedding creation
Hi @Eigenket27 ,
If you use the model = AutoModel.from_pretrained('intfloat/multilingual-e5-large') instead of git pull, it should only download the necessary files.
In case you use git pull, you can rm -rf .git onnx/ *.safetensors if you do not need advanced features.
what comes in advanced features? I have been using this model for embedding creation and reranking
Oh, I was referring to using ONNX inference or creating git pull requests.