CocoRoF / lo_SimCSE_test

huggingface.co
Total runs: 13
24-hour runs: 1
7-day runs: -9
30-day runs: -33
Model's Last Updated: February 03 2025
sentence-similarity

Introduction of lo_SimCSE_test

Model Details of lo_SimCSE_test

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
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity
Model Sources
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 ๐Ÿค— Hub
model = SentenceTransformer("x2bee/sts_nli_tune_test")
# Run inference
sentences = [
    '๋ฒ„์Šค๊ฐ€ ๋ฐ”์œ ๊ธธ์„ ๋”ฐ๋ผ ์šด์ „ํ•œ๋‹ค.',
    '๋…น์ƒ‰ ๋ฒ„์Šค๊ฐ€ ๋„๋กœ๋ฅผ ๋”ฐ๋ผ ๋‚ด๋ ค๊ฐ„๋‹ค.',
    '๊ทธ ์—ฌ์ž๋Š” ๋ฐ์ดํŠธํ•˜๋Ÿฌ ๊ฐ€๋Š” ์ค‘์ด๋‹ค.',
]
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]
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
    ๊ฐœ๋…์ ์œผ๋กœ ํฌ๋ฆผ ์Šคํ‚ค๋ฐ์€ ์ œํ’ˆ๊ณผ ์ง€๋ฆฌ๋ผ๋Š” ๋‘ ๊ฐ€์ง€ ๊ธฐ๋ณธ ์ฐจ์›์„ ๊ฐ€์ง€๊ณ  ์žˆ๋‹ค. ์ œํ’ˆ๊ณผ ์ง€๋ฆฌํ•™์€ ํฌ๋ฆผ ์Šคํ‚ค๋ฐ์„ ์ž‘๋™์‹œํ‚ค๋Š” ๊ฒƒ์ด๋‹ค. 0.5
    ์‹œ์ฆŒ ์ค‘์— ์•Œ๊ณ  ์žˆ๋Š” ๊ฑฐ ์•Œ์•„? ๋„ค ๋ ˆ๋ฒจ์—์„œ ๋‹ค์Œ ๋ ˆ๋ฒจ๋กœ ์žƒ์–ด๋ฒ„๋ฆฌ๋Š” ๊ฑฐ์•ผ ๋ธŒ๋ ˆ์ด๋ธŒ์Šค๊ฐ€ ๋ชจํŒ€์„ ๋– ์˜ฌ๋ฆฌ๊ธฐ๋กœ ๊ฒฐ์ •ํ•˜๋ฉด ๋ธŒ๋ ˆ์ด๋ธŒ์Šค๊ฐ€ ํŠธ๋ฆฌํ”Œ A์—์„œ ํ•œ ๋‚จ์ž๋ฅผ ๋– ์˜ฌ๋ฆฌ๊ธฐ๋กœ ๊ฒฐ์ •ํ•˜๋ฉด ๋”๋ธ” A๊ฐ€ ๊ทธ๋ฅผ ๋Œ€์‹ ํ•˜๋Ÿฌ ์˜ฌ๋ผ๊ฐ€๊ณ  A ํ•œ ๋ช…์ด ๊ทธ๋ฅผ ๋Œ€์‹ ํ•˜๋Ÿฌ ์˜ฌ๋ผ๊ฐ„๋‹ค. ์‚ฌ๋žŒ๋“ค์ด ๊ธฐ์–ตํ•˜๋ฉด ๋‹ค์Œ ์ˆ˜์ค€์œผ๋กœ ๋ฌผ๊ฑด์„ ์žƒ๋Š”๋‹ค. 1.0
    ์šฐ๋ฆฌ ๋ฒˆํ˜ธ ์ค‘ ํ•˜๋‚˜๊ฐ€ ๋‹น์‹ ์˜ ์ง€์‹œ๋ฅผ ์„ธ๋ฐ€ํ•˜๊ฒŒ ์ˆ˜ํ–‰ํ•  ๊ฒƒ์ด๋‹ค. ์šฐ๋ฆฌ ํŒ€์˜ ์ผ์›์ด ๋‹น์‹ ์˜ ๋ช…๋ น์„ ์—„์ฒญ๋‚˜๊ฒŒ ์ •ํ™•ํ•˜๊ฒŒ ์‹คํ–‰ํ•  ๊ฒƒ์ด๋‹ค. 1.0
  • Loss: CosineSimilarityLoss 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: 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
  • Samples:
    text pair label
    ์•ˆ์ „๋ชจ๋ฅผ ๊ฐ€์ง„ ํ•œ ๋‚จ์ž๊ฐ€ ์ถค์„ ์ถ”๊ณ  ์žˆ๋‹ค. ์•ˆ์ „๋ชจ๋ฅผ ์“ด ํ•œ ๋‚จ์ž๊ฐ€ ์ถค์„ ์ถ”๊ณ  ์žˆ๋‹ค. 1.0
    ์–ด๋ฆฐ์•„์ด๊ฐ€ ๋ง์„ ํƒ€๊ณ  ์žˆ๋‹ค. ์•„์ด๊ฐ€ ๋ง์„ ํƒ€๊ณ  ์žˆ๋‹ค. 0.95
    ํ•œ ๋‚จ์ž๊ฐ€ ๋ฑ€์—๊ฒŒ ์ฅ๋ฅผ ๋จน์ด๊ณ  ์žˆ๋‹ค. ๋‚จ์ž๊ฐ€ ๋ฑ€์—๊ฒŒ ์ฅ๋ฅผ ๋จน์ด๊ณ  ์žˆ๋‹ค. 1.0
  • Loss: CosineSimilarityLoss 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",
}

Runs of CocoRoF lo_SimCSE_test on huggingface.co

13
Total runs
1
24-hour runs
1
3-day runs
-9
7-day runs
-33
30-day runs

More Information About lo_SimCSE_test huggingface.co Model

lo_SimCSE_test huggingface.co

lo_SimCSE_test huggingface.co is an AI model on huggingface.co that provides lo_SimCSE_test's model effect (), which can be used instantly with this CocoRoF lo_SimCSE_test model. huggingface.co supports a free trial of the lo_SimCSE_test model, and also provides paid use of the lo_SimCSE_test. Support call lo_SimCSE_test model through api, including Node.js, Python, http.

lo_SimCSE_test huggingface.co Url

https://huggingface.co/CocoRoF/lo_SimCSE_test

CocoRoF lo_SimCSE_test online free

lo_SimCSE_test huggingface.co is an online trial and call api platform, which integrates lo_SimCSE_test's modeling effects, including api services, and provides a free online trial of lo_SimCSE_test, you can try lo_SimCSE_test online for free by clicking the link below.

CocoRoF lo_SimCSE_test online free url in huggingface.co:

https://huggingface.co/CocoRoF/lo_SimCSE_test

lo_SimCSE_test install

lo_SimCSE_test is an open source model from GitHub that offers a free installation service, and any user can find lo_SimCSE_test on GitHub to install. At the same time, huggingface.co provides the effect of lo_SimCSE_test install, users can directly use lo_SimCSE_test installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

lo_SimCSE_test install url in huggingface.co:

https://huggingface.co/CocoRoF/lo_SimCSE_test

Url of lo_SimCSE_test

lo_SimCSE_test huggingface.co Url

Provider of lo_SimCSE_test huggingface.co

CocoRoF
ORGANIZATIONS

Other API from CocoRoF

huggingface.co

Total runs: 15
Run Growth: -29
Growth Rate: -193.33%
Updated:February 18 2025
huggingface.co

Total runs: 13
Run Growth: 8
Growth Rate: 61.54%
Updated:January 22 2025
huggingface.co

Total runs: 5
Run Growth: -5
Growth Rate: -100.00%
Updated:March 21 2025
huggingface.co

Total runs: 3
Run Growth: 0
Growth Rate: 0.00%
Updated:February 02 2025