Quangnguyen711 / nothing-mutilingua

SentenceTransformer based on distilbert/distilbert-base-multilingual-cased

This is a sentence-transformers model finetuned from distilbert/distilbert-base-multilingual-cased . 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: distilbert/distilbert-base-multilingual-cased
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

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': 512, 'do_lower_case': False, 'architecture': 'DistilBertModel'})
  (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 🤗 Hub
model = SentenceTransformer("Quangnguyen711/nothing-mutilingua")
# Run inference
sentences = [
    'while drying himself off with a towel and about to change suddenly ah',
    'vừa lau khô người bằng khăn và định thay đồ đột nhiên ah',
    'và cứ thế vị khách không mời mà đến rời khỏi ký túc xá của ha jun',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.8401, -0.0778],
#         [ 0.8401,  1.0000, -0.0855],
#         [-0.0778, -0.0855,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,816 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 4 tokens mean: 19.05 tokens max: 70 tokens	min: 4 tokens mean: 22.26 tokens max: 82 tokens

• Samples:

  sentence_0	sentence_1
  standing there with a flushed face and hands covering her eyes was jooah	đứng đó với khuôn mặt đỏ ửng và hai tay che mắt là joo ah
  how come i asked	sao vậy tôi hỏi
  the challenges anna faced would certainly mature her mentally	những thử thách anna đối mặt chắc chắn sẽ giúp cô ấy trưởng thành về mặt tinh thần

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy : steps
• per_device_train_batch_size : 256
• per_device_eval_batch_size : 256
• num_train_epochs : 50
• batch_sampler : no_duplicates
• multi_dataset_batch_sampler : round_robin

All Hyperparameters

Training Logs

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.1.1
• Transformers: 4.57.0
• PyTorch: 2.8.0+cu126
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.22.1

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}
}