Sentence Similarity
sentence-transformers
PyTorch
TensorFlow
Transformers
bert
feature-extraction
text-embeddings-inference
Instructions to use jhgan/ko-sbert-multitask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use jhgan/ko-sbert-multitask with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("jhgan/ko-sbert-multitask") 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] - Transformers
How to use jhgan/ko-sbert-multitask with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("jhgan/ko-sbert-multitask") model = AutoModel.from_pretrained("jhgan/ko-sbert-multitask") - Inference
- Notebooks
- Google Colab
- Kaggle
| epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman | |
| 0,-1,0.8659228032591821,0.8652234715800531,0.8427037577716313,0.8488446438962325,0.8430641774102295,0.8488621350114751,0.818989534778603,0.8184396745689155 | |
| 1,-1,0.862757009696124,0.8638814670856595,0.8457022500896411,0.8517688683290012,0.8456828584686157,0.8515828183788728,0.8154770450664813,0.8139087212721753 | |
| 2,-1,0.8647729788447694,0.8659954045026031,0.8506331785344513,0.8562043286774481,0.8505907830208431,0.8559509334852342,0.8184021322674964,0.8157329680794658 | |
| 3,-1,0.8636746481730748,0.8648858912735103,0.8494365514027341,0.8553624907800136,0.8497561323796402,0.8555135274902032,0.8218193945785947,0.8198186114611435 | |
| 4,-1,0.8647378896165001,0.8656049006716164,0.8502137332449051,0.8563097949422148,0.8506006255629878,0.8563336935351775,0.8250650034150077,0.823458765054616 | |