How to use moka-ai/m3e-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("moka-ai/m3e-base") 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]
目前，8核32G的配置，单条速度约400ms左右，我是转onnx模型后，使用go-onnxruntime库加载的模型
我能想到比较简单的实现也是 ONNX ，其他的方法只学习过，没有实践过。
· Sign up or log in to comment
