Sponsored by AdsCreator.com
Toolify Toolify logo
AI Models
ParaRook-ja-uk

bicolino34 / ParaRook-ja-uk

Run on huggingface.co
huggingface.co
Total runs: 20
24-hour runs: 0
7-day runs: 0
30-day runs: 3
Model's Last Updated: May 07 2025
sentence-similarity

Introduction of ParaRook-ja-uk

Model Details of ParaRook-ja-uk

SentenceTransformer based on sentence-transformers/LaBSE

This is a sentence-transformers model finetuned from sentence-transformers/LaBSE on the csv 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: sentence-transformers/LaBSE
  • Maximum Sequence Length: 256 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity
  • Training Dataset:
    • csv
Model Sources
Full Model Architecture 
SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, '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'})
  (3): Normalize()
)
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("bicolino34/ParaRook-ja-uk")
# Run inference
sentences = [
    '「つまり、自分の娘が誰かにレイプされることを両親が認めた。',
    '— Тобто батьки дозволили, щоб хтось ґвалтував їхню дочку?',
    'Оскільки відмова повторювалася не один раз, то, природно, ніхто його нікуди не запрошував.',
]
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
csv
  • Dataset: csv
  • Size: 11,973 training samples
  • Columns: Source and Target
  • Approximate statistics based on the first 1000 samples:
    Source Target
    type string string
    details
    • min: 4 tokens
    • mean: 22.71 tokens
    • max: 147 tokens
    • min: 4 tokens
    • mean: 20.0 tokens
    • max: 132 tokens
  • Samples:
    Source Target
    「おっしゃるとおりです」 — Правду кажете.
    それが、梯子を二三段上って見ると、上では誰か火をとぼして、しかもその火をそこここと動かしているらしい。 Проте, ступивши кілька щаблів вище, він помітив, ніби там хтось не тільки засвітив вогник, але ще й ним водить.
    「結果的にはそういうことになるかもしれない」 — Можливо, так у підсумку й вийде.
  • Loss: MultipleNegativesRankingLoss with these parameters: 
    {
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}
Evaluation Dataset
csv
  • Dataset: csv
  • Size: 1,331 evaluation samples
  • Columns: Source and Target
  • Approximate statistics based on the first 1000 samples:
    Source Target
    type string string
    details
    • min: 3 tokens
    • mean: 22.32 tokens
    • max: 123 tokens
    • min: 3 tokens
    • mean: 19.29 tokens
    • max: 94 tokens
  • Samples:
    Source Target
    「そして私たちはその人物を野放しにしておくことはできない」 — Але ми не можемо залишити його в спокої.
    まだ生理は始まっていませんから、ほとんど手つかずであるはずです。 Оскільки в неї ще не почалося місячне, вони залишаються неторканими.
    「たとえばだね、草というものは黒い土から出るのだがなぜこう青いもんだろう。 – От, скажімо, трава. Вона росте з чорної землі, чому ж вона зелена?
  • Loss: MultipleNegativesRankingLoss with these parameters: 
    {
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}
Training Hyperparameters
Non-Default Hyperparameters
  • eval_strategy : steps
  • per_device_train_batch_size : 16
  • per_device_eval_batch_size : 16
  • warmup_ratio : 0.1
  • fp16 : True
  • batch_sampler : no_duplicates
All Hyperparameters
Click to expand
  • overwrite_output_dir : False
  • do_predict : False
  • eval_strategy : steps
  • prediction_loss_only : True
  • per_device_train_batch_size : 16
  • per_device_eval_batch_size : 16
  • 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 : 1.0
  • num_train_epochs : 3
  • 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 : False
  • 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}
  • tp_size : 0
  • 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 : None
  • hub_always_push : False
  • 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
  • eval_use_gather_object : False
  • average_tokens_across_devices : False
  • prompts : None
  • batch_sampler : no_duplicates
  • multi_dataset_batch_sampler : proportional
Training Logs
Epoch Step Training Loss Validation Loss
0.1335 100 0.0907 0.0628
0.2670 200 0.0659 0.0772
0.4005 300 0.0639 0.0692
0.5340 400 0.0674 0.0798
0.6676 500 0.0881 0.0726
0.8011 600 0.0838 0.0670
0.9346 700 0.0933 0.0710
1.0681 800 0.0604 0.0698
1.2016 900 0.0357 0.0717
1.3351 1000 0.0241 0.0718
1.4686 1100 0.0295 0.0720
1.6021 1200 0.0169 0.0566
1.7356 1300 0.0203 0.0618
1.8692 1400 0.0202 0.0604
2.0027 1500 0.0179 0.0568
2.1362 1600 0.0137 0.0523
2.2697 1700 0.0104 0.0548
2.4032 1800 0.0096 0.0536
2.5367 1900 0.0095 0.0519
2.6702 2000 0.0071 0.0489
2.8037 2100 0.014 0.0500
2.9372 2200 0.0123 0.0504
Framework Versions
  • Python: 3.11.12
  • Sentence Transformers: 3.4.1
  • Transformers: 4.51.3
  • PyTorch: 2.6.0+cu124
  • Accelerate: 1.6.0
  • Datasets: 3.5.1
  • Tokenizers: 0.21.1
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",
}
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}
}

Runs of bicolino34 ParaRook-ja-uk on huggingface.co

20
Total runs
0
24-hour runs
-2
3-day runs
0
7-day runs
3
30-day runs

More Information About ParaRook-ja-uk huggingface.co Model

ParaRook-ja-uk huggingface.co

ParaRook-ja-uk huggingface.co is an AI model on huggingface.co that provides ParaRook-ja-uk's model effect (), which can be used instantly with this bicolino34 ParaRook-ja-uk model. huggingface.co supports a free trial of the ParaRook-ja-uk model, and also provides paid use of the ParaRook-ja-uk. Support call ParaRook-ja-uk model through api, including Node.js, Python, http.

ParaRook-ja-uk huggingface.co Url

https://huggingface.co/bicolino34/ParaRook-ja-uk

bicolino34 ParaRook-ja-uk online free

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

bicolino34 ParaRook-ja-uk online free url in huggingface.co:

https://huggingface.co/bicolino34/ParaRook-ja-uk

ParaRook-ja-uk install

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

ParaRook-ja-uk install url in huggingface.co:

https://huggingface.co/bicolino34/ParaRook-ja-uk

Url of ParaRook-ja-uk

ParaRook-ja-uk huggingface.co Url

Provider of ParaRook-ja-uk huggingface.co

bicolino34
ORGANIZATIONS
huggingface.co

Other API from bicolino34