Sentence Similarity
sentence-transformers
Safetensors
Korean
xlm-roberta
feature-extraction
dataset_size:1K<n<10K
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use harheem/bge-m3-nvidia-ko-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use harheem/bge-m3-nvidia-ko-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("harheem/bge-m3-nvidia-ko-v1") sentences = [ "하이브리다이저란 무엇인가요?", "하이퍼바이저는 보안에서 어떤 역할을 합니까?", "지난 몇 년간 CUDA 생태계는 어떻게 발전해 왔나요?", "로컬 메모리 액세스 성능을 결정하는 요소는 무엇입니까?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from harheem/bge-m3-nvidia-ko-v1: direct link, hf CLI and curl.
- Browser
- Download file 5.37 kB
-
https://huggingface.co/harheem/bge-m3-nvidia-ko-v1/resolve/main/training_args.bin
- Command line
-
hf download hf://harheem/bge-m3-nvidia-ko-v1/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/harheem/bge-m3-nvidia-ko-v1/resolve/main/training_args.bin
5.37 kB
- Xet hash:
- 406653d32bdc7f10127a806ab4f1d392729811560e0a5cf42b84f3b4b1cf924f
- Size of remote file:
- 5.37 kB
- SHA256:
- 05f202436de7622733f700da9f93c1e602a5522cfe8e9d878dddc3d88bf451f1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.