Model reference · open weights

KR-SBERT-Medium-extended-klueNLItriplet_PARpair_QApair-klueSTS

Available as managed deployment Embeddings snunlp · community Embeddings 1 variants 1k dl/mo

KR-SBERT-Medium-extended-klueNLItriplet_PARpair_QApair-klueSTS is an open-weight embedding model from snunlp. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bysnunlp
TypeEmbedding models
TaskEmbeddings
Parameters (lead)117M
Context512 tokens
Runs withsentence-transformers
Released2024-07-31
Popularity1k downloads / month
LicenceUnknown

About

What KR-SBERT-Medium-extended-klueNLItriplet_PARpair_QApair-klueSTS is

This is a sentence-transformers model trained on the klue/klue dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Read the full model card

Model Details

Model Description

  • Model Type: Sentence Transformer

  • Maximum Sequence Length: 512 tokens

  • Output Dimensionality: 768 tokens

  • Similarity Function: Cosine Similarity

  • Training Dataset:

  • Language: ko

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("snunlp/KR-SBERT-Medium-extended-klueNLItriplet_PARpair_QApair-klueSTS")
# Run inference
sentences = [
    'SR은 동대구·김천구미·신경주역에서 승하차하는 모든 국민에게 운임 10%를 할인해 준다.',
    'SR은 동대구역, 김천구미역, 신주역을 오가는 모든 승객을 대상으로 요금을 10% 할인해 드립니다.',
    '수강신청 하는 날짜가 어느 날짜인지 아시는지요?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity
MetricValue
pearson_cosine0.8786
spearman_cosine0.8765
pearson_manhattan0.8589
spearman_manhattan0.8582
pearson_euclidean0.8595
spearman_euclidean0.8597
pearson_dot0.8518
spearman_dot0.8479
pearson_max0.8786
spearman_max0.8765

Training Details

Training Dataset

klue/klue
  • Dataset: klue/klue at 349481e
  • Size: 11,668 training samples
  • Columns: sentence1, sentence2, and label
  • Approximate statistics based on the first 1000 samples:
    sentence1sentence2label
    typestringstringfloat
    detailsmin: 7 tokensmean: 18.12 tokensmax: 56 tokensmin: 6 tokensmean: 17.58 tokensmax: 60 tokensmin: 0.0mean: 0.44max: 1.0
  • Samples:
    sentence1sentence2label
    숙소 위치는 찾기 쉽고 일반적인 한국의 반지하 숙소입니다.숙박시설의 위치는 쉽게 찾을 수 있고 한국의 대표적인 반지하 숙박시설입니다.0.7428571428571428
    위반행위 조사 등을 거부·방해·기피한 자는 500만원 이하 과태료 부과 대상이다.시민들 스스로 자발적인 예방 노력을 한 것은 아산 뿐만이 아니었다.0.0
    회사가 보낸 메일은 이 지메일이 아니라 다른 지메일 계정으로 전달해줘.사람들이 주로 네이버 메일을 쓰는 이유를 알려줘0.06666666666666667
  • Loss: CosineSimilarityLoss with these parameters:
    {
        "loss_fct": "torch.nn.modules.loss.MSELoss"
    }
    

Evaluation Dataset

klue/klue
  • Dataset: klue/klue at 349481e
  • Size: 519 evaluation samples
  • Columns: sentence1, sentence2, and label
  • Approximate statistics based on the first 1000 samples:
    sentence1sentence2label
    typestring

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Semantic Similaritysts devPearson Cosine0.879
Semantic Similaritysts devSpearman Cosine0.877
Semantic Similaritysts devPearson Manhattan0.859
Semantic Similaritysts devSpearman Manhattan0.858
Semantic Similaritysts devPearson Euclidean0.860
Semantic Similaritysts devSpearman Euclidean0.860
Semantic Similaritysts devPearson Dot0.852
Semantic Similaritysts devSpearman Dot0.848
Semantic Similaritysts devPearson Max0.879
Semantic Similaritysts devSpearman Max0.877

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys kr-sbert-medium-extended-kluenlitriplet-parpair-qapair-kluests for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kr-sbert-medium-extended-kluenlitriplet-parpair-qapair-kluests below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kr-sbert-medium-extended-kluenlitriplet-parpair-qapair-kluests","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms