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]
因为想用昇腾芯片去跑这个模型，Sentence Transormers的代码还没有支撑npu。但我用Transformer运行时，发现输出的向量差别比较大，不知道咋回事
· Sign up or log in to comment
