josangho99/ko-paraphrase-multilingual-MiniLM-L12-v2-multiTask

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
• —Maximum Sequence Length: 128 tokens
• —Output Dimensionality: 384 dimensions
• —Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - 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': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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 🤗 Hub
model = SentenceTransformer("josangho99/ko-paraphrase-multilingual-MiniLM-L12-v2-multiTask")
# Run inference
sentences = [
    '소년이 볼링을 치고 있다.',
    '몇몇 구경꾼들과 함께 건물 안에서 볼링을 치는 젊은 아프리카계 미국인 소년.',
    '한 소년이 핀볼을 하고 있다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5878, 0.6530],
#         [0.5878, 1.0000, 0.4061],
#         [0.6530, 0.4061, 1.0000]])

<!--

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 Datasets

Unnamed Dataset

• —Size: 568,640 training samples
• —Columns: <code>sentence0</code>, <code>sentence1</code>, and <code>sentence_2</code>
• —Approximate statistics based on the first 1000 samples: | | sentence0 | sentence1 | sentence_2 | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 4 tokens</li><li>mean: 20.25 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 19.22 tokens</li><li>max: 90 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 14.49 tokens</li><li>max: 46 tokens</li></ul> |
• —Samples: | sentence0 | sentence1 | sentence_2 | |:------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------| | <code>그 나라는 교황과의 투쟁으로 두 그룹으로 나뉘었다.</code> | <code>교황권과의 그의 권력 투쟁은 국가를 교황을 지지하는 두 개의 매우 변덕스러운 수용소와 황제를 지지하는 기벨린으로 나누었다.</code> | <code>그 나라는 권력 투쟁에도 불구하고 단결된 상태를 유지했다.</code> | | <code>여자가 커피를 엎지른다</code> | <code>벤치에 앉아 있는 청바지를 입은 여성이 커피를 쏟는 것에 반응한다.</code> | <code>남자가 커피를 엎지른다</code> | | <code>노란 건물 앞에서 걸어가는 여자.</code> | <code>그 건물은 노란색이다.</code> | <code>여자가 파란 집 안에 앉아 있다.</code> |
• —Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Unnamed Dataset

• —Size: 5,749 training samples
• —Columns: <code>sentence0</code>, <code>sentence1</code>, and <code>label</code>
• —Approximate statistics based on the first 1000 samples: | | sentence0 | sentence1 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 6 tokens</li><li>mean: 18.89 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 18.91 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
• —Samples: | sentence0 | sentence1 | label | |:---------------------------------------------------------------------|:--------------------------------------------------------|:--------------------------------| | <code>마감일이 다가오면서 재정 절벽 거래에 투표하는 미국 상원</code> | <code>재정 절벽 : 주택 지연 재정 절벽 거래에 대한 투표 - 라이브</code> | <code>0.5599999999999999</code> | | <code>이것은 미국, 내 친구들입니다.그리고 여기서는 일어나지 말아야 합니다."그는 큰 박수를 보냈습니다.</code> | <code>"이건 미국이야, 내 친구들. 그리고 여기서는 그런 일이 일어나면 안 돼."</code> | <code>0.65</code> | | <code>보스턴 마라톤 뉴스에 대한 어린이들의 이야기 돕기 책</code> | <code>보스턴 마라톤 결승선에서 발생한 두 번의 폭발 보고</code> | <code>0.16</code> |
• —Loss: <code>CosineSimilarityLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —num_train_epochs: 5
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: round_robin

All Hyperparameters

<details><summary>Click to expand</summary>

• —overwrite_output_dir: False
• —do_predict: False
• —eval_strategy: steps
• —prediction_loss_only: True
• —per_device_train_batch_size: 8
• —per_device_eval_batch_size: 8
• —per_gpu_train_batch_size: None
• —per_gpu_eval_batch_size: None
• —gradient_accumulation_steps: 1
• —eval_accumulation_steps: None
• —torch_empty_cache_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
• —num_train_epochs: 5
• —max_steps: -1
• —lr_scheduler_type: linear
• —lr_scheduler_kwargs: {}
• —warmup_ratio: 0.0
• —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: False
• —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: False
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —deepspeed: None
• —label_smoothing_factor: 0.0
• —optim: adamwtorchfused
• —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: None
• —hub_always_push: False
• —hub_revision: None
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —include_inputs_for_metrics: False
• —include_for_metrics: []
• —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
• —include_tokens_per_second: False
• —include_num_input_tokens_seen: False
• —neftune_noise_alpha: None
• —optim_target_modules: None
• —batch_eval_metrics: False
• —eval_on_start: False
• —use_liger_kernel: False
• —liger_kernel_config: None
• —eval_use_gather_object: False
• —average_tokens_across_devices: False
• —prompts: None
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: round_robin
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

Framework Versions

• —Python: 3.12.11
• —Sentence Transformers: 5.1.0
• —Transformers: 4.56.1
• —PyTorch: 2.8.0+cu126
• —Accelerate: 1.10.1
• —Datasets: 4.0.0
• —Tokenizers: 0.22.0

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

<!--

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. -->