Downloads · 30 days
51
2% of all-time downloads
snunlp/KLUE-SRoBERTa-Large-SNUExtended-klueNLI-klueSTS
KLUE-SRoBERTa-Large-SNUExtended-klueNLI-klueSTS is a sentence similarity model from snunlp. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model trained on the klue/klue dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphr…
Downloads · 30 days
51
2% of all-time downloads
All-time downloads
3.2K
Public
Parameters
356M
1.4 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors1.4 GB · 99%
From the Hugging Face model README
This is a sentence-transformers model trained on the klue/klue 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.
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
(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})
)
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("snunlp/KLUE-SRoBERTa-Large-SNUExtended-klueNLI-klueSTS")
# Run inference
sentences = [
'SR은 동대구·김천구미·신경주역에서 승하차하는 모든 국민에게 운임 10%를 할인해 준다.',
'SR은 동대구역, 김천구미역, 신주역을 오가는 모든 승객을 대상으로 요금을 10% 할인해 드립니다.',
'수강신청 하는 날짜가 어느 날짜인지 아시는지요?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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.*
-->
sts-dev| Metric | Value |
|---|---|
| pearson_cosine | 0.8423 |
| spearman_cosine | 0.8422 |
| pearson_manhattan | 0.816 |
| spearman_manhattan | 0.819 |
| pearson_euclidean | 0.8155 |
| spearman_euclidean | 0.8181 |
| pearson_dot | 0.7793 |
| spearman_dot | 0.7861 |
| pearson_max | 0.8423 |
| spearman_max | 0.8422 |
| sentence1 | sentence2 | label | |
|---|---|---|---|
| type | string | string | float |
| details | <ul><li>min: 8 tokens</li><li>mean: 22.48 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 21.92 tokens</li><li>max: 67 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.44</li><li>max: 1.0</li></ul> |
| sentence1 | sentence2 | label |
|---|---|---|
| <code>숙소 위치는 찾기 쉽고 일반적인 한국의 반지하 숙소입니다.</code> | <code>숙박시설의 위치는 쉽게 찾을 수 있고 한국의 대표적인 반지하 숙박시설입니다.</code> | <code>0.7428571428571428</code> |
| <code>위반행위 조사 등을 거부·방해·기피한 자는 500만원 이하 과태료 부과 대상이다.</code> | <code>시민들 스스로 자발적인 예방 노력을 한 것은 아산 뿐만이 아니었다.</code> | <code>0.0</code> |
| <code>회사가 보낸 메일은 이 지메일이 아니라 다른 지메일 계정으로 전달해줘.</code> | <code>사람들이 주로 네이버 메일을 쓰는 이유를 알려줘</code> | <code>0.06666666666666667</code> |
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
| sentence1 | sentence2 | label | |
|---|---|---|---|
| type | string | string | float |
| details | <ul><li>min: 8 tokens</li><li>mean: 22.45 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 21.86 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
| sentence1 | sentence2 | label |
|---|---|---|
| <code>무엇보다도 호스트분들이 너무 친절하셨습니다.</code> | <code>무엇보다도, 호스트들은 매우 친절했습니다.</code> | <code>0.9714285714285713</code> |
| <code>주요 관광지 모두 걸어서 이동가능합니다.</code> | <code>위치는 피렌체 중심가까지 걸어서 이동 가능합니다.</code> | <code>0.2857142857142858</code> |
| <code>학생들의 균형 있는 영어능력을 향상시킬 수 있는 학교 수업을 유도하기 위해 2018학년도 수능부터 도입된 영어 영역 절대평가는 올해도 유지한다.</code> | <code>영어 영역의 경우 학생들이 한글 해석본을 암기하는 문제를 해소하기 위해 2016학년도부터 적용했던 EBS 연계 방식을 올해도 유지한다.</code> | <code>0.25714285714285723</code> |
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
eval_strategy: stepsper_device_train_batch_size: 32per_device_eval_batch_size: 32num_train_epochs: 10warmup_ratio: 0.1fp16: Trueload_best_model_at_end: Trueoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 32per_device_eval_batch_size: 32per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 10max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.1warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Trueignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Falsehub_always_push: Falsegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseeval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Nonedispatch_batches: Nonesplit_batches: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falsebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportional| Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine |
|---|---|---|---|---|
| 0 | 0 | - | - | 0.2962 |
| 0.0109 | 1 | 0.0487 | - | - |
| 0.2732 | 50 | 0.0472 | 0.0748 | 0.5629 |
| 0.5464 | 100 | 0.0299 | 0.0433 | 0.7509 |
| 0.8197 | 150 | 0.0207 | 0.0361 | 0.7955 |
| 1.0929 | 200 | 0.0184 | 0.0341 | 0.7998 |
| 1.3661 | 250 | 0.0129 | 0.0352 | 0.7952 |
| 1.6393 | 300 | 0.0125 | 0.0337 | 0.8120 |
| 1.9126 | 350 | 0.0117 | 0.0319 | 0.8254 |
| 2.1858 | 400 | 0.0091 | 0.0311 | 0.8300 |
| 2.4590 | 450 | 0.0071 | 0.0316 | 0.8380 |
| 2.7322 | 500 | 0.0072 | 0.0318 | 0.8300 |
| 3.0055 | 550 | 0.007 | 0.0331 | 0.8261 |
| 3.2787 | 600 | 0.0066 | 0.0309 | 0.8299 |
| 3.5519 | 650 | 0.006 | 0.0309 | 0.8414 |
| 3.8251 | 700 | 0.0056 | 0.0336 | 0.8262 |
| 4.0984 | 750 | 0.0054 | 0.0344 | 0.8348 |
| 4.3716 | 800 | 0.0049 | 0.0305 | 0.8397 |
| 4.6448 | 850 | 0.0047 | 0.0295 | 0.8408 |
| 4.9180 | 900 | 0.0044 | 0.0295 | 0.8411 |
| 5.1913 | 950 | 0.0044 | 0.0326 | 0.8302 |
| 5.4645 | 1000 | 0.004 | 0.0303 | 0.8393 |
| 5.7377 | 1050 | 0.0037 | 0.0300 | 0.8408 |
| 6.0109 | 1100 | 0.0033 | 0.0310 | 0.8419 |
| 6.2842 | 1150 | 0.0032 | 0.0296 | 0.8377 |
| 6.5574 | 1200 | 0.003 | 0.0286 | 0.8441 |
| 6.8306 | 1250 | 0.0028 | 0.0294 | 0.8414 |
| 7.1038 | 1300 | 0.0027 | 0.0301 | 0.8420 |
| 7.3770 | 1350 | 0.0023 | 0.0305 | 0.8450 |
| 7.6503 | 1400 | 0.0022 | 0.0296 | 0.8443 |
| 7.9235 | 1450 | 0.002 | 0.0290 | 0.8460 |
| 8.1967 | 1500 | 0.0017 | 0.0305 | 0.8422 |
@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.*
-->