This is a sentence-transformers model finetuned from answerdotai/ModernBERT-base on the korean_nli_dataset 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.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: answerdotai/ModernBERT-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': True, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("x2bee/sts_nli_tune_test")
# Run inference
sentences = [
    '버스가 바쁜 길을 따라 운전한다.',
    '녹색 버스가 도로를 따라 내려간다.',
    '그 여자는 데이트하러 가는 중이다.',
]
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

Dataset: sts_dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8273
spearman_cosine	0.8298
pearson_euclidean	0.8112
spearman_euclidean	0.8214
pearson_manhattan	0.8125
spearman_manhattan	0.8226
pearson_dot	0.7648
spearman_dot	0.7648
pearson_max	0.8273
spearman_max	0.8298

Training Details

Training Dataset

korean_nli_dataset

Dataset: korean_nli_dataset at ef305ef
Size: 392,702 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 4 tokens
mean: 35.7 tokens
max: 194 tokens
min: 4 tokens
mean: 19.92 tokens
max: 64 tokens
min: 0.0
mean: 0.48
max: 1.0

Samples:

sentence1	sentence2	score
`개념적으로 크림 스키밍은 제품과 지리라는 두 가지 기본 차원을 가지고 있다.`	`제품과 지리학은 크림 스키밍을 작동시키는 것이다.`	`0.5`
`시즌 중에 알고 있는 거 알아? 네 레벨에서 다음 레벨로 잃어버리는 거야 브레이브스가 모팀을 떠올리기로 결정하면 브레이브스가 트리플 A에서 한 남자를 떠올리기로 결정하면 더블 A가 그를 대신하러 올라가고 A 한 명이 그를 대신하러 올라간다.`	`사람들이 기억하면 다음 수준으로 물건을 잃는다.`	`1.0`
`우리 번호 중 하나가 당신의 지시를 세밀하게 수행할 것이다.`	`우리 팀의 일원이 당신의 명령을 엄청나게 정확하게 실행할 것이다.`	`1.0`

Loss: CosineSimilarityLoss with these parameters:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

Evaluation Dataset

sts_dev

Dataset: sts_dev at 1de0cdf
Size: 1,500 evaluation samples
Columns: text, pair, and label
Approximate statistics based on the first 1000 samples:
text pair label
type string string float
details
min: 7 tokens
mean: 20.38 tokens
max: 52 tokens
min: 6 tokens
mean: 20.52 tokens
max: 54 tokens
min: 0.0
mean: 0.42
max: 1.0