| --- |
| tags: |
| - sentence-transformers |
| - sparse-encoder |
| - sparse |
| - splade |
| - generated_from_trainer |
| - dataset_size:104550 |
| - loss:SpladeLoss |
| - loss:SparseMultipleNegativesRankingLoss |
| - loss:FlopsLoss |
| base_model: distilbert/distilbert-base-multilingual-cased |
| widget: |
| - text: يُعتبر التأثير الأوروبي على الثقافة اليابانية في القرن التاسع عشر أمرًا هامًا |
| في فهم تاريخ البلاد. |
| - text: "\n\n يعد النقد الأدبي أداة أساسية في فهم التاريخ الثقافي، حيث يعكس التغيرات\ |
| \ الاجتماعية والثقافية التي حدثت عبر العصور." |
| - text: لا أعتقد أن هناك أي تأثير لصالح المصممة الداخلية الإيطالية إيلينا فرونتزي |
| على هذا النوع من التصاميم. |
| - text: كيف يؤثر النقد الأدبي على التفاعل الاجتماعي؟ |
| - text: "\n\n يعد النقد الأدبي أداة أساسية في فهم التاريخ الثقافي، حيث يساعد على تحليل\ |
| \ وتفسير الأعمال الفنية والثقافية من خلال منظور تاريخي." |
| datasets: |
| - oddadmix/arabic-triplets-large |
| pipeline_tag: feature-extraction |
| library_name: sentence-transformers |
| --- |
| |
| # SPLADE Sparse Encoder |
|
|
| This is a [SPLADE Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the [arabic-triplets-large](https://huggingface.co/datasets/oddadmix/arabic-triplets-large) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 119547-dimensional sparse vector space and can be used for semantic search and sparse retrieval. |
| ## Model Details |
|
|
| ### Model Description |
| - **Model Type:** SPLADE Sparse Encoder |
| - **Base model:** [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) <!-- at revision 45c032ab32cc946ad88a166f7cb282f58c753c2e --> |
| - **Maximum Sequence Length:** 512 tokens |
| - **Output Dimensionality:** 119547 dimensions |
| - **Similarity Function:** Dot Product |
| - **Supported Modality:** Text |
| - **Training Dataset:** |
| - [arabic-triplets-large](https://huggingface.co/datasets/oddadmix/arabic-triplets-large) |
| <!-- - **Language:** Unknown --> |
| <!-- - **License:** Unknown --> |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Documentation:** [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| - **Hugging Face:** [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| SparseEncoder( |
| (0): Transformer({'transformer_task': 'fill-mask', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'token_embeddings', 'architecture': 'DistilBertForMaskedLM'}) |
| (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'embedding_dimension': 119547}) |
| ) |
| ``` |
|
|
| ## Usage |
|
|
| ### Direct Usage (Sentence Transformers) |
|
|
| First install the Sentence Transformers library: |
|
|
| ```bash |
| pip install -U sentence-transformers |
| ``` |
| Then you can load this model and run inference. |
| ```python |
| from sentence_transformers import SparseEncoder |
| |
| # Download from the 🤗 Hub |
| model = SparseEncoder("sparse_encoder_model_id") |
| # Run inference |
| sentences = [ |
| 'ما هي أهمية النقد الأدبي في فهم التاريخ الثقافي؟', |
| '\n\n يعد النقد الأدبي أداة أساسية في فهم التاريخ الثقافي، حيث يساعد على تحليل وتفسير الأعمال الفنية والثقافية من خلال منظور تاريخي.', |
| 'تُعتبر اللغة العربية لغة قديمة ومتنوعة، وتمثل جزءًا هامًا من تراث البشرية.', |
| ] |
| embeddings = model.encode(sentences) |
| print(embeddings.shape) |
| # [3, 119547] |
| |
| # Get the similarity scores for the embeddings |
| similarities = model.similarity(embeddings, embeddings) |
| print(similarities) |
| # tensor([[ 43.2637, 49.1410, 12.4760], |
| # [ 49.1410, 113.4840, 30.3306], |
| # [ 12.4760, 30.3306, 109.0792]]) |
| ``` |
| <!-- |
| ### 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.* |
| --> |
|
|
| <!-- |
| ## 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 Dataset |
|
|
| #### arabic-triplets-large |
|
|
| * Dataset: [arabic-triplets-large](https://huggingface.co/datasets/oddadmix/arabic-triplets-large) at [fa99ede](https://huggingface.co/datasets/oddadmix/arabic-triplets-large/tree/fa99ede10602ff5cffb7591ff1f25289414c4b13) |
| * Size: 104,550 training samples |
| * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> |
| * Approximate statistics based on the first 100 samples: |
| | | anchor | positive | negative | |
| |:---------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| |
| | type | string | string | string | |
| | modality | text | text | text | |
| | details | <ul><li>min: 12 tokens</li><li>mean: 18.6 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 26 tokens</li><li>mean: 57.26 tokens</li><li>max: 142 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 47.38 tokens</li><li>max: 120 tokens</li></ul> | |
| * Samples: |
| | anchor | positive | negative | |
| |:----------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| | <code>ما هي أهمية التلال والمناطق الجبلية في البيئة؟</code> | <code><br><br> تعتبر التلال والمناطق الجبلية من أهم عناصر البيئة التي تؤثر بشكل كبير على توازن النظام الإيكولوجي.</code> | <code>يعتبر النشاط السياسي في البلدان الصغيرة من الأمور التي تتطلب إدارة شاملة ومتكاملة.</code> | |
| | <code>كيف تؤثر التلال على الرياح والهطول المطر؟</code> | <code><br><br> يؤثر التلال على الرياح والهطول المطر من خلال تأثيرهم على توزيع الضغط الجوي، مما يؤدي إلى تغييرات في اتجاه وسرعة الرياح وتواتر الهطول.</code> | <code>إنّ الأنشطة الزراعية في المناطق الجبلية تعتبر من أهمّ العوامل التي تساهم في تحسين جودة الحياة في هذه المناطق، ولكنها لا تؤثر بشكل مباشر على الرياح والهطول المطر.</code> | |
| | <code>ما هي أنواع التلال المختلفة؟ (جبال، هضاب، منحدرات)</code> | <code><br><br> هناك ثلاثة أنواع رئيسية للتلاءم هي الجبال، الهضاب، والمنحدرات.</code> | <code>الإدارة البيئية تعتبر من الأنشطة التي لها تأثير كبير على البيئة.</code> | |
| * Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters: |
| ```json |
| { |
| "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False, directions=('query_to_doc',), partition_mode='joint', hardness_mode=None, hardness_strength=0.0)", |
| "document_regularizer_weight": 3e-05, |
| "query_regularizer_weight": 5e-05 |
| } |
| ``` |
|
|
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
|
|
| - `per_device_train_batch_size`: 16 |
| - `num_train_epochs`: 1 |
| - `learning_rate`: 2e-05 |
| - `gradient_accumulation_steps`: 4 |
| - `batch_sampler`: no_duplicates |
| |
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
| |
| - `per_device_train_batch_size`: 16 |
| - `num_train_epochs`: 1 |
| - `max_steps`: -1 |
| - `learning_rate`: 2e-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`: 4 |
| - `average_tokens_across_devices`: True |
| - `max_grad_norm`: 1.0 |
| - `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`: trackio |
| - `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_backend`: None |
| - `ddp_timeout`: 1800 |
| - `fsdp`: [] |
| - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
| - `deepspeed`: None |
| - `debug`: [] |
| - `skip_memory_metrics`: True |
| - `do_predict`: False |
| - `resume_from_checkpoint`: None |
| - `warmup_ratio`: None |
| - `local_rank`: -1 |
| - `prompts`: None |
| - `batch_sampler`: no_duplicates |
| - `multi_dataset_batch_sampler`: proportional |
| - `router_mapping`: {} |
| - `learning_rate_mapping`: {} |
|
|
| </details> |
|
|
| ### Training Logs |
| | Epoch | Step | Training Loss | |
| |:------:|:----:|:-------------:| |
| | 0.3060 | 500 | 7.9967 | |
|
|
|
|
| ### Training Time |
| - **Training**: 8.3 minutes |
|
|
| ### Framework Versions |
| - Python: 3.12.3 |
| - Sentence Transformers: 5.5.1 |
| - Transformers: 5.5.0 |
| - PyTorch: 2.12.0+cu130 |
| - Accelerate: 1.14.0 |
| - Datasets: 4.3.0 |
| - Tokenizers: 0.22.2 |
|
|
| ## Additional Resources |
|
|
| - [Training and Finetuning Sparse Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sparse-encoder): the end-to-end guide for training or finetuning SPLADE and other sparse encoder models. |
|
|
| ## Citation |
|
|
| ### BibTeX |
|
|
| #### Sentence Transformers |
| ```bibtex |
| @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", |
| } |
| ``` |
|
|
| #### SpladeLoss |
| ```bibtex |
| @misc{formal2022distillationhardnegativesampling, |
| title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective}, |
| author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant}, |
| year={2022}, |
| eprint={2205.04733}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.IR}, |
| url={https://arxiv.org/abs/2205.04733}, |
| } |
| ``` |
|
|
| #### SparseMultipleNegativesRankingLoss |
| ```bibtex |
| @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}, |
| } |
| ``` |
|
|
| #### FlopsLoss |
| ```bibtex |
| @article{paria2020minimizing, |
| title={Minimizing flops to learn efficient sparse representations}, |
| author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s}, |
| journal={arXiv preprint arXiv:2004.05665}, |
| year={2020} |
| } |
| ``` |
|
|
| <!-- |
| ## 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.* |
| --> |
