Sentence Similarity
sentence-transformers
Safetensors
Korean
qwen3_vl
feature-extraction
Generated from Trainer
dataset_size:708729
loss:MatryoshkaLoss
loss:CachedMultipleNegativesRankingLoss
Eval Results (legacy)
Instructions to use whybe-choi/Qwen3-VL-Embedding-2B-ko-vdr-preview-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use whybe-choi/Qwen3-VL-Embedding-2B-ko-vdr-preview-v0.3 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("whybe-choi/Qwen3-VL-Embedding-2B-ko-vdr-preview-v0.3") sentences = [ "공공외교법 제6조 및 제12조에 따른 기본계획 수립과 한국국제교류재단(KF)의 역할, 한러 협력 전략, 다부처 협력 과제들이 어떻게 공공외교의 통합적 추진 체계 강화에 기여했나요?", "data/images/ko/ko-vdr-public/5364.png", "data/images/ko/ko-vdr-public/5369.png", "data/images/ko/ko-vdr-public/6349.png", "data/images/ko/ko-vdr-public/5357.png", "data/images/ko/ko-vdr-public/5356.png", "data/images/ko/ko-vdr-public/904.png", "data/images/ko/ko-vdr-public/886.png", "data/images/ko/ko-vdr-public/5379.png" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [9, 9] - Notebooks
- Google Colab
- Kaggle
Ctrl+K