How to use intfloat/e5-small-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("intfloat/e5-small-v2") 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]
What is the best way to use the ONNX model?embeddings = HuggingFaceEmbeddings(model_name='intfloat/e5-small-v2', model_kwargs = {'device': 'gpu:0'})
Sorry but I am not familiar with ONNX, the ONNX model was contributed by the community.
· Sign up or log in to comment
