Sentence-Transformers

Snippets

埋め込み層のパラメータ数

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("cl-nagoya/sup-simcse-ja-base")
embeddings = model[0]._modules['auto_model'].embeddings
sum([param.numel()
     for param in embeddings.parameters()
     if param.requires_grad])