sigridjineth/ModernBERT-korean-large-preview

SentenceTransformer based on answerdotai/ModernBERT-large

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-large on the korean_nli_dataset_reranker_v1 dataset. It maps sentences & paragraphs to a 1024-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-large <!-- at revision f87846cf8be76fceb18718f0245d18c8e6571215 -->
• —Maximum Sequence Length: 8192 tokens
• —Output Dimensionality: 1024 dimensions
• —Similarity Function: Cosine Similarity
• —Training Dataset:
• —korean_nli_dataset_reranker_v1
• —Language: ko <!-- - 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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)

Evaluation

Metrics

AutoRAG Retrieval

Triplet

• —Dataset: dev-eval
• —Evaluated with <code>TripletEvaluator</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

• —Size: 1,120,235 training samples
• —Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
• —Approximate statistics based on the first 1000 samples: | | query | positive | negative | |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 5 tokens</li><li>mean: 55.49 tokens</li><li>max: 476 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 186.0 tokens</li><li>max: 1784 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 120.54 tokens</li><li>max: 2383 tokens</li></ul> |
• —Samples: | query | positive | negative | |:-------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------| | <code>양복을 입은 노인이 짐을 뒤로 끌고 간다.</code> | <code>양복을 입은 남자</code> | <code>옷을 입은 노인</code> | | <code>한국의 제1위 서비스 수출 시장은 중국이니</code> | <code>중국은 세계 제2위의 서비스 교역국이자 우리나라의 제1위 서비스 수출 시장으로서,<br> 2016년 중국의 서비스교역 규모는 6,571억불로 미국(12,145억불)에 이어 세계 2위<br> 중국 서비스산업의 GDP대비 비중은 2015년 50% 돌파, 서비스산업 성장률 98.3%) > GDP 성장률(6.9%)<br>* 2016년 서비스 분야 우리의 對中수출(206억불)은 對세계수출(949억불)의 22%<br>ㅇ 네거티브 방식의 포괄적인 서비스 투자 개방 협정이 중국과 체결될 경우, 양국간 상호 서비스 시장 개방 수준을 높이고, 우리 투자 기업에 대한 실질적 보호를 한층 강화할 수 있을 것으로 기대된다.</code> | <code>우리나라에서 중국으로 수출되는 제품은 점점 계속 증가하고 있다.</code> | | <code>아버지, 병원, 치료, 받다, 결심하다</code> | <code>너무나 아팠던 아버지는 병원에서 치료를 받기로 결심했다.</code> | <code>요즘, 아버지, 건강, 걱정</code> |
• —Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }

Training Logs

Framework Versions

• —Python: 3.11.9
• —Sentence Transformers: 3.3.1
• —Transformers: 4.48.0.dev0
• —PyTorch: 2.3.0+cu121
• —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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

<!--

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. -->