Downloads · 30 days
65
18% of all-time downloads
fransquill/multilingual-biencoder-semantic-similarity-xlmr-finetuned-v1
multilingual-biencoder-semantic-similarity-xlmr-finetuned-v1 is a sentence similarity model from fransquill. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as apache-2.0.
Fine-tuned multilingual bi-encoder for semantic similarity.
Downloads · 30 days
65
18% of all-time downloads
All-time downloads
355
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 99%
From the Hugging Face model README
Fine-tuned multilingual bi-encoder for semantic similarity.
Base model: sentence-transformers/stsb-xlm-r-multilingual
from sentence_transformers import SentenceTransformer, util
model = SentenceTransformer("fransquill/multilingual-biencoder-semantic-similarity-xlmr-finetuned-v1")
sentences = ["The cat sits on the mat", "A feline is resting on a rug"]
emb = model.encode(sentences)
print(util.cos_sim(emb[0], emb[1]))