SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: intfloat/multilingual-e5-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'قرآن شراب اور جوئے کے بارے میں کیا کہتا ہے؟',
    'O you who have believed, indeed, intoxicants, gambling, [sacrificing on] stone alters [to other than Allah], and divining arrows are but defilement from the work of Satan, so avoid it that you may be successful.',
    'عَنِ الْخَيْرِ، وَكُنْتُ أَسْأَلُهُ عَنِ الشَّرِّ، مَخَافَةَ أَنْ يُدْرِكَنِي فَقُلْتُ يَا رَسُولَ اللَّهِ إِنَّا كُنَّا فِي جَاهِلِيَّةٍ وَشَرٍّ فَجَاءَنَا اللَّهُ بِهَذَا الْخَيْرِ، فَهَلْ بَعْدَ هَذَا الْخَيْرِ مِنْ شَرٍّ قَالَ \u200f"\u200f نَعَمْ \u200f"\u200f\u200f.\u200f قُلْتُ وَهَلْ بَعْدَ ذَلِكَ الشَّرِّ مِنْ خَيْرٍ قَالَ \u200f"\u200f نَعَمْ، وَفِيهِ دَخَنٌ \u200f"\u200f\u200f.\u200f قُلْتُ وَمَا دَخَنُهُ قَالَ \u200f"\u200f قَوْمٌ',
]
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, 0.6190, 0.1344],
#         [0.6190, 1.0000, 0.1736],
#         [0.1344, 0.1736, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 801 training samples
• Columns: sentence_0, sentence_1, and sentence_2
• Approximate statistics based on the first 100 samples:

  	sentence_0	sentence_1	sentence_2
  type	string	string	string
  modality	text	text	text
  details	min: 7 tokensmean: 13.95 tokensmax: 24 tokens	min: 12 tokensmean: 107.9 tokensmax: 512 tokens	min: 14 tokensmean: 179.42 tokensmax: 512 tokens

• Samples:

  sentence_0	sentence_1	sentence_2
  هل يأمر القرآن بالعدل ولو على الأقربين؟	O you who have believed, be persistently standing firm in justice, witnesses for Allah, even if it be against yourselves or parents and relatives. Whether one is rich or poor, Allah is more worthy of both. So follow not [personal] inclination, lest you not be just. And if you distort [your testimony] or refuse [to give it], then indeed Allah is ever, with what you do, Acquainted.	رَسُولَ اللَّهِ صلى الله عليه وسلم قَالَ ‏ "‏ لاَ صَلاَةَ لِمَنْ لَمْ يَقْرَأْ بِأُمِّ الْقُرْآنِ ‏"‏ ‏.‏
  متى تصلى صلاة الوتر؟	Ibn 'Umar reported the Messenger of Allah (ﷺ) as say- ing:Hasten to pray Witr before morning	سَقَتْ رَسُولَ اللَّهِ صلى الله عليه وسلم أَنْقَعَتْ لَهُ تَمَرَاتٍ مِنَ اللَّيْلِ، فَلَمَّا أَكَلَ سَقَتْهُ إِيَّاهُ‏.‏
  ما هي الغيبة؟	Abu Huraira reported Allah's Messenger (ﷺ) as saying:Do you know what is backbiting? They (the Companions) said: Allah and His Messenger know best. Thereupon he (the Holy Prophet) said: Backbiting implies your talking about your brother in a manner which he does not like. It was said to him: What is your opinion about this that if I actually find (that failing) in my brother which I made a mention of? He said: If (that failing) is actually found (in him) what you assert, you in fact backbited him, and if that is not in him it is a slander	غَافِرِ ٱلذَّنۢبِ وَقَابِلِ ٱلتَّوْبِ شَدِيدِ ٱلْعِقَابِ ذِى ٱلطَّوْلِ ۖ لَآ إِلَٰهَ إِلَّا هُوَ ۖ إِلَيْهِ ٱلْمَصِيرُ

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• multi_dataset_batch_sampler: round_robin

All Hyperparameters

• per_device_train_batch_size: 8
• num_train_epochs: 3
• max_steps: -1
• learning_rate: 5e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1
• label_smoothing_factor: 0.0
• bf16: False
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: None
• trackio_bucket_id: None
• trackio_static_space_id: None
• per_device_eval_batch_size: 8
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_static_graph: None
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: None
• fsdp_config: None
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Time

• Training: 6.5 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.7.0
• Transformers: 5.13.1
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

Additional Resources

• Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
• Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
• Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
• Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
• Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}