snunlp / KR-SBERT-Medium-klueNLI-klueSTS

huggingface.co
Total runs: 96
24-hour runs: 0
7-day runs: 2
30-day runs: 85
Model's Last Updated: June 19 2024
sentence-similarity

Introduction of KR-SBERT-Medium-klueNLI-klueSTS

Model Details of KR-SBERT-Medium-klueNLI-klueSTS

SentenceTransformer

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.

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 ๐Ÿค— Hub
model = SentenceTransformer("snunlp/KR-SBERT-Medium-klueNLI-klueSTS")
# Run inference
sentences = [
    'SR์€ ๋™๋Œ€๊ตฌยท๊น€์ฒœ๊ตฌ๋ฏธยท์‹ ๊ฒฝ์ฃผ์—ญ์—์„œ ์Šนํ•˜์ฐจํ•˜๋Š” ๋ชจ๋“  ๊ตญ๋ฏผ์—๊ฒŒ ์šด์ž„ 10%๋ฅผ ํ• ์ธํ•ด ์ค€๋‹ค.',
    'SR์€ ๋™๋Œ€๊ตฌ์—ญ, ๊น€์ฒœ๊ตฌ๋ฏธ์—ญ, ์‹ ์ฃผ์—ญ์„ ์˜ค๊ฐ€๋Š” ๋ชจ๋“  ์Šน๊ฐ์„ ๋Œ€์ƒ์œผ๋กœ ์š”๊ธˆ์„ 10% ํ• ์ธํ•ด ๋“œ๋ฆฝ๋‹ˆ๋‹ค.',
    '์ˆ˜๊ฐ•์‹ ์ฒญ ํ•˜๋Š” ๋‚ ์งœ๊ฐ€ ์–ด๋А ๋‚ ์งœ์ธ์ง€ ์•„์‹œ๋Š”์ง€์š”?',
]
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
Metric Value
pearson_cosine 0.8476
spearman_cosine 0.8546
pearson_manhattan 0.7968
spearman_manhattan 0.7966
pearson_euclidean 0.7969
spearman_euclidean 0.7972
pearson_dot 0.7564
spearman_dot 0.7638
pearson_max 0.8476
spearman_max 0.8546
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:
    sentence1 sentence2 label
    type string string float
    details
    • min: 7 tokens
    • mean: 18.53 tokens
    • max: 56 tokens
    • min: 6 tokens
    • mean: 18.02 tokens
    • max: 60 tokens
    • min: 0.0
    • mean: 0.44
    • max: 1.0
  • Samples:
    sentence1 sentence2 label
    ์ˆ™์†Œ ์œ„์น˜๋Š” ์ฐพ๊ธฐ ์‰ฝ๊ณ  ์ผ๋ฐ˜์ ์ธ ํ•œ๊ตญ์˜ ๋ฐ˜์ง€ํ•˜ ์ˆ™์†Œ์ž…๋‹ˆ๋‹ค. ์ˆ™๋ฐ•์‹œ์„ค์˜ ์œ„์น˜๋Š” ์‰ฝ๊ฒŒ ์ฐพ์„ ์ˆ˜ ์žˆ๊ณ  ํ•œ๊ตญ์˜ ๋Œ€ํ‘œ์ ์ธ ๋ฐ˜์ง€ํ•˜ ์ˆ™๋ฐ•์‹œ์„ค์ž…๋‹ˆ๋‹ค. 0.7428571428571428
    ์œ„๋ฐ˜ํ–‰์œ„ ์กฐ์‚ฌ ๋“ฑ์„ ๊ฑฐ๋ถ€ยท๋ฐฉํ•ดยท๊ธฐํ”ผํ•œ ์ž๋Š” 500๋งŒ์› ์ดํ•˜ ๊ณผํƒœ๋ฃŒ ๋ถ€๊ณผ ๋Œ€์ƒ์ด๋‹ค. ์‹œ๋ฏผ๋“ค ์Šค์Šค๋กœ ์ž๋ฐœ์ ์ธ ์˜ˆ๋ฐฉ ๋…ธ๋ ฅ์„ย ํ•œ ๊ฒƒ์€ ์•„์‚ฐ ๋ฟ๋งŒ์ด ์•„๋‹ˆ์—ˆ๋‹ค. 0.0
    ํšŒ์‚ฌ๊ฐ€ ๋ณด๋‚ธ ๋ฉ”์ผ์€ ์ด ์ง€๋ฉ”์ผ์ด ์•„๋‹ˆ๋ผ ๋‹ค๋ฅธ ์ง€๋ฉ”์ผ ๊ณ„์ •์œผ๋กœ ์ „๋‹ฌํ•ด์ค˜. ์‚ฌ๋žŒ๋“ค์ด ์ฃผ๋กœ ๋„ค์ด๋ฒ„ ๋ฉ”์ผ์„ ์“ฐ๋Š” ์ด์œ ๋ฅผ ์•Œ๋ ค์ค˜ 0.06666666666666667
  • 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:
    sentence1 sentence2 label
    type string string float
    details
    • min: 7 tokens
    • mean: 18.6 tokens
    • max: 61 tokens
    • min: 7 tokens
    • mean: 18.16 tokens
    • max: 60 tokens
    • min: 0.0
    • mean: 0.5
    • max: 1.0
  • Samples:
    sentence1 sentence2 label
    ๋ฌด์—‡๋ณด๋‹ค๋„ ํ˜ธ์ŠคํŠธ๋ถ„๋“ค์ด ๋„ˆ๋ฌด ์นœ์ ˆํ•˜์…จ์Šต๋‹ˆ๋‹ค. ๋ฌด์—‡๋ณด๋‹ค๋„, ํ˜ธ์ŠคํŠธ๋“ค์€ ๋งค์šฐ ์นœ์ ˆํ–ˆ์Šต๋‹ˆ๋‹ค. 0.9714285714285713
    ์ฃผ์š” ๊ด€๊ด‘์ง€ ๋ชจ๋‘ ๊ฑธ์–ด์„œ ์ด๋™๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค. ์œ„์น˜๋Š” ํ”ผ๋ Œ์ฒด ์ค‘์‹ฌ๊ฐ€๊นŒ์ง€ ๊ฑธ์–ด์„œ ์ด๋™ ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค. 0.2857142857142858
    ํ•™์ƒ๋“ค์˜ ๊ท ํ˜• ์žˆ๋Š” ์˜์–ด๋Šฅ๋ ฅ์„ ํ–ฅ์ƒ์‹œํ‚ฌ ์ˆ˜ ์žˆ๋Š” ํ•™๊ต ์ˆ˜์—…์„ ์œ ๋„ํ•˜๊ธฐ ์œ„ํ•ด 2018ํ•™๋…„๋„ ์ˆ˜๋Šฅ๋ถ€ํ„ฐ ๋„์ž…๋œ ์˜์–ด ์˜์—ญ ์ ˆ๋Œ€ํ‰๊ฐ€๋Š” ์˜ฌํ•ด๋„ ์œ ์ง€ํ•œ๋‹ค. ์˜์–ด ์˜์—ญ์˜ ๊ฒฝ์šฐ ํ•™์ƒ๋“ค์ด ํ•œ๊ธ€ ํ•ด์„๋ณธ์„ ์•”๊ธฐํ•˜๋Š” ๋ฌธ์ œ๋ฅผ ํ•ด์†Œํ•˜๊ธฐ ์œ„ํ•ด 2016ํ•™๋…„๋„๋ถ€ํ„ฐ ์ ์šฉํ–ˆ๋˜ EBS ์—ฐ๊ณ„ ๋ฐฉ์‹์„ ์˜ฌํ•ด๋„ ์œ ์ง€ํ•œ๋‹ค. 0.25714285714285723
  • Loss: CosineSimilarityLoss with these parameters:
    {
        "loss_fct": "torch.nn.modules.loss.MSELoss"
    }
    
Training Hyperparameters
Non-Default Hyperparameters
  • eval_strategy : steps
  • per_device_train_batch_size : 64
  • per_device_eval_batch_size : 64
  • num_train_epochs : 10
  • warmup_ratio : 0.1
  • fp16 : True
  • load_best_model_at_end : True
All Hyperparameters
Click to expand
  • overwrite_output_dir : False
  • do_predict : False
  • eval_strategy : steps
  • prediction_loss_only : True
  • per_device_train_batch_size : 64
  • per_device_eval_batch_size : 64
  • per_gpu_train_batch_size : None
  • per_gpu_eval_batch_size : None
  • gradient_accumulation_steps : 1
  • eval_accumulation_steps : None
  • learning_rate : 5e-05
  • weight_decay : 0.0
  • adam_beta1 : 0.9
  • adam_beta2 : 0.999
  • adam_epsilon : 1e-08
  • max_grad_norm : 1.0
  • num_train_epochs : 10
  • max_steps : -1
  • lr_scheduler_type : linear
  • lr_scheduler_kwargs : {}
  • warmup_ratio : 0.1
  • warmup_steps : 0
  • log_level : passive
  • log_level_replica : warning
  • log_on_each_node : True
  • logging_nan_inf_filter : True
  • save_safetensors : True
  • save_on_each_node : False
  • save_only_model : False
  • restore_callback_states_from_checkpoint : False
  • no_cuda : False
  • use_cpu : False
  • use_mps_device : False
  • seed : 42
  • data_seed : None
  • jit_mode_eval : False
  • use_ipex : False
  • bf16 : False
  • fp16 : True
  • fp16_opt_level : O1
  • half_precision_backend : auto
  • bf16_full_eval : False
  • fp16_full_eval : False
  • tf32 : None
  • local_rank : 0
  • ddp_backend : None
  • tpu_num_cores : None
  • tpu_metrics_debug : False
  • debug : []
  • dataloader_drop_last : False
  • dataloader_num_workers : 0
  • dataloader_prefetch_factor : None
  • past_index : -1
  • disable_tqdm : False
  • remove_unused_columns : True
  • label_names : None
  • load_best_model_at_end : True
  • ignore_data_skip : False
  • fsdp : []
  • fsdp_min_num_params : 0
  • fsdp_config : {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap : None
  • accelerator_config : {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • deepspeed : None
  • label_smoothing_factor : 0.0
  • optim : adamw_torch
  • optim_args : None
  • adafactor : False
  • group_by_length : False
  • length_column_name : length
  • ddp_find_unused_parameters : None
  • ddp_bucket_cap_mb : None
  • ddp_broadcast_buffers : False
  • dataloader_pin_memory : True
  • dataloader_persistent_workers : False
  • skip_memory_metrics : True
  • use_legacy_prediction_loop : False
  • push_to_hub : False
  • resume_from_checkpoint : None
  • hub_model_id : None
  • hub_strategy : every_save
  • hub_private_repo : False
  • hub_always_push : False
  • gradient_checkpointing : False
  • gradient_checkpointing_kwargs : None
  • include_inputs_for_metrics : False
  • eval_do_concat_batches : True
  • fp16_backend : auto
  • push_to_hub_model_id : None
  • push_to_hub_organization : None
  • mp_parameters :
  • auto_find_batch_size : False
  • full_determinism : False
  • torchdynamo : None
  • ray_scope : last
  • ddp_timeout : 1800
  • torch_compile : False
  • torch_compile_backend : None
  • torch_compile_mode : None
  • dispatch_batches : None
  • split_batches : None
  • include_tokens_per_second : False
  • include_num_input_tokens_seen : False
  • neftune_noise_alpha : None
  • optim_target_modules : None
  • batch_eval_metrics : False
  • batch_sampler : batch_sampler
  • multi_dataset_batch_sampler : proportional
Training Logs
Epoch Step Training Loss loss sts-dev_spearman_cosine
0 0 - - 0.2874
0.0109 1 0.1046 - -
0.5435 50 0.0703 0.0605 0.6007
1.0870 100 0.0203 0.0340 0.8140
1.6304 150 0.0118 0.0304 0.8342
2.1739 200 0.0094 0.0298 0.8480
2.7174 250 0.0054 0.0311 0.8503
3.2609 300 0.0048 0.0303 0.8488
3.8043 350 0.0043 0.0307 0.8526
4.3478 400 0.0035 0.0305 0.8515
4.8913 450 0.0033 0.0302 0.8513
5.4348 500 0.0028 0.0306 0.8546
Framework Versions
  • Python: 3.11.9
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.0.1
  • Accelerate: 0.31.0
  • Datasets: 2.19.1
  • Tokenizers: 0.19.1
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 snunlp KR-SBERT-Medium-klueNLI-klueSTS on huggingface.co

96
Total runs
0
24-hour runs
0
3-day runs
2
7-day runs
85
30-day runs

More Information About KR-SBERT-Medium-klueNLI-klueSTS huggingface.co Model

KR-SBERT-Medium-klueNLI-klueSTS huggingface.co

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

KR-SBERT-Medium-klueNLI-klueSTS huggingface.co Url

https://huggingface.co/snunlp/KR-SBERT-Medium-klueNLI-klueSTS

snunlp KR-SBERT-Medium-klueNLI-klueSTS online free

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

snunlp KR-SBERT-Medium-klueNLI-klueSTS online free url in huggingface.co:

https://huggingface.co/snunlp/KR-SBERT-Medium-klueNLI-klueSTS

KR-SBERT-Medium-klueNLI-klueSTS install

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

KR-SBERT-Medium-klueNLI-klueSTS install url in huggingface.co:

https://huggingface.co/snunlp/KR-SBERT-Medium-klueNLI-klueSTS

Url of KR-SBERT-Medium-klueNLI-klueSTS

KR-SBERT-Medium-klueNLI-klueSTS huggingface.co Url

Provider of KR-SBERT-Medium-klueNLI-klueSTS huggingface.co

snunlp
ORGANIZATIONS

Other API from snunlp

huggingface.co

Total runs: 165.4K
Run Growth: -191.9K
Growth Rate: -116.07%
Updated:April 28 2022
huggingface.co

Total runs: 350
Run Growth: 218
Growth Rate: 62.29%
Updated:November 22 2021
huggingface.co

Total runs: 348
Run Growth: -75
Growth Rate: -21.55%
Updated:April 28 2022
huggingface.co

Total runs: 11
Run Growth: 6
Growth Rate: 54.55%
Updated:March 24 2024
huggingface.co

Total runs: 7
Run Growth: 3
Growth Rate: 42.86%
Updated:March 24 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:May 31 2024