ํ๊ตญ์ด์ ์์ด์ nli, sts๋ฐ์ดํฐ๋ฅผ klue/roberta-base์ ํ์ต์ํจ ๋ชจ๋ธ์ ๋๋ค.
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
query = ['๊ทธ๋ ๊ทธ๋
๋ฅผ ์ข์ํ๋ค.']
sentences = ["he love her", "he hate her", '๊ทธ๋
๋ ๊ทธ๋ฅผ ์ซ์ดํ๋ค.','attention is all you need']
emb1 = model.encode(query)
emb2 = model.encode(sentences)
print(cosine_similarity(emb1,emb2))
-> array([[0.62751913, 0.23996451, 0.30788696, 0.08123618]], dtype=float32)
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.