KoModernBERT-base-mlm-ecs-simcse

SentenceTransformer based on answerdotai/ModernBERT-base

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 <!-- at revision addb15798678d7f76904915cf8045628d402b3ce -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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.

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]

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Semantic Similarity

• Dataset: sts_dev
• Evaluated with <code>EmbeddingSimilarityEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

korean_nli_dataset

• Dataset: korean_nli_dataset at ef305ef
• Size: 392,702 training samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	<ul><li>min: 4 tokens</li><li>mean: 35.7 tokens</li><li>max: 194 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 19.92 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.48</li><li>max: 1.0</li></ul>

• Samples:

  sentence1	sentence2	score
  <code>개념적으로 크림 스키밍은 제품과 지리라는 두 가지 기본 차원을 가지고 있다.</code>	<code>제품과 지리학은 크림 스키밍을 작동시키는 것이다.</code>	<code>0.5</code>
  <code>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.</code>	<code>사람들이 기억하면 다음 수준으로 물건을 잃는다.</code>	<code>1.0</code>
  <code>우리 번호 중 하나가 당신의 지시를 세밀하게 수행할 것이다.</code>	<code>우리 팀의 일원이 당신의 명령을 엄청나게 정확하게 실행할 것이다.</code>	<code>1.0</code>

• Loss: <code>CosineSimilarityLoss</code> with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Dataset

sts_dev

• Dataset: sts_dev at 1de0cdf
• Size: 1,500 evaluation samples
• Columns: <code>text</code>, <code>pair</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	text	pair	label
  type	string	string	float
  details	<ul><li>min: 7 tokens</li><li>mean: 20.38 tokens</li><li>max: 52 tokens</li></ul>	<ul><li>min: 6 tokens</li><li>mean: 20.52 tokens</li><li>max: 54 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul>

• Samples:

  text	pair	label
  <code>안전모를 가진 한 남자가 춤을 추고 있다.</code>	<code>안전모를 쓴 한 남자가 춤을 추고 있다.</code>	<code>1.0</code>
  <code>어린아이가 말을 타고 있다.</code>	<code>아이가 말을 타고 있다.</code>	<code>0.95</code>
  <code>한 남자가 뱀에게 쥐를 먹이고 있다.</code>	<code>남자가 뱀에게 쥐를 먹이고 있다.</code>	<code>1.0</code>

• Loss: <code>CosineSimilarityLoss</code> with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Framework Versions

• Python: 3.11.10
• Sentence Transformers: 3.3.1
• Transformers: 4.48.0
• PyTorch: 2.5.1+cu124
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->