Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:49962
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use PerRing/e5_ko with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use PerRing/e5_ko with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("PerRing/e5_ko") sentences = [ "query: 잡지는 인종차별적이고 성차별적인 유머를 제공했다.", "passage: 잡지는 인종과 성별에 대해 편견적인 농담을 실었다.", "passage: 잡지는 모든 사람을 존중하는 유머를 제공했다.", "passage: 그들은 중요하지만 활용도가 낮은 데이터를 보유하고 있었다." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download modules.json from PerRing/e5_ko: direct link, hf CLI and curl.
- Browser
- Download file 349 Bytes
-
https://huggingface.co/PerRing/e5_ko/resolve/main/modules.json
- Command line
-
hf download hf://PerRing/e5_ko/modules.json
-
curl -L -o modules.json https://huggingface.co/PerRing/e5_ko/resolve/main/modules.json
349 Bytes
| [ | |
| { | |
| "idx": 0, | |
| "name": "0", | |
| "path": "", | |
| "type": "sentence_transformers.models.Transformer" | |
| }, | |
| { | |
| "idx": 1, | |
| "name": "1", | |
| "path": "1_Pooling", | |
| "type": "sentence_transformers.models.Pooling" | |
| }, | |
| { | |
| "idx": 2, | |
| "name": "2", | |
| "path": "2_Normalize", | |
| "type": "sentence_transformers.models.Normalize" | |
| } | |
| ] |