Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation
Paper • 2004.09813 • Published • 1
This is a bge-base model trained to have mutlilingual semantic abilities, specifically the Yoruba Language An implementation of https://arxiv.org/abs/2004.09813, Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation
- Downloads last month
- 86
from sentence_transformers import SentenceTransformer model = SentenceTransformer("odunola/yoruba-embedding-model") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]