Feature Extraction
sentence-transformers
PyTorch
English
bert
splade
sparse-encoder
sparse
text-embeddings-inference
Instructions to use naver/splade-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use naver/splade-v3 with sentence-transformers:
from sentence_transformers import SparseEncoder model = SparseEncoder("naver/splade-v3") queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Inference
- Notebooks
- Google Colab
- Kaggle
How can I use just the embedding process?
#3
by leopaz - opened
Hi,
Sorry if i'm missing something obvious here but how can i make this model generate sparse vector embeddings and not do inference?
hi @leopaz
I am not sure I 100% understood your question, but you can for instance follow the notebook here (https://github.com/naver/splade/blob/main/inference_splade.ipynb) to generate sparse vectors w/ SPLADE.
hope it helps!
tformal changed discussion status to closed