| --- |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - dense |
| - generated_from_trainer |
| - dataset_size:102127 |
| - loss:SpladeLoss |
| - loss:SparseMultipleNegativesRankingLoss |
| - loss:FlopsLoss |
| base_model: seregadgl/splade_gemma_google_base_checkpoint_100_clear |
| widget: |
| - source_sentence: 'query: 6460338 acdelco' |
| sentences: |
| - 'document: очиститель тормозов rsqprofessional арт 072589767pl volkswagen id buzz |
| янтарный' |
| - 'document: гтц 6460338 для chevrolet traverse' |
| - 'document: гтц 6960358 для chevrolet traverse' |
| - source_sentence: 'query: audioquest cinnamon usb 0 7500 см ' |
| sentences: |
| - 'document: кабель usb аудиоквест cinnamon 0 7500 см 8712516' |
| - 'document: задняя камера рамке номерного знака интерпауэр ip616 54785862' |
| - 'document: аудиокабель soundwave 200 см' |
| - source_sentence: 'query: акустическое пианино weber w 121 pw ' |
| sentences: |
| - 'document: акустическое пианино steinway model s' |
| - 'document: инструмент для игры на пианино вебер w 121 pw' |
| - 'document: велосипед сильвербек strela sport 700c 54 см blue 60097000435025' |
| - source_sentence: 'query: шкаф шрм24' |
| sentences: |
| - 'document: wardrobe shrm 24 4348563' |
| - 'document: духовой шкаф бертаццони f6011provtn' |
| - 'document: шкаф мдф30' |
| - source_sentence: 'query: 1452634 santool jawa 300 cl' |
| sentences: |
| - 'document: смартфон эппл iphone xs max 512gb' |
| - 'document: 1453934 santool съемник для сальников jawa 300 cl' |
| - 'document: 1452634 santool съемник для сальников jawa 300 cl' |
| datasets: |
| - seregadgl/car_and_product_triplet_103k |
| pipeline_tag: sentence-similarity |
| library_name: sentence-transformers |
| metrics: |
| - cosine_accuracy@1 |
| - cosine_precision@1 |
| - cosine_precision@3 |
| - cosine_precision@5 |
| - cosine_precision@10 |
| - cosine_recall@1 |
| - cosine_recall@3 |
| - cosine_recall@5 |
| - cosine_recall@10 |
| - cosine_ndcg@10 |
| - cosine_mrr@10 |
| - cosine_map@100 |
| model-index: |
| - name: SentenceTransformer based on seregadgl/splade_gemma_google_base_checkpoint_100_clear |
| results: |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: val set fine |
| type: val_set_fine |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.749 |
| name: Cosine Accuracy@1 |
| - type: cosine_precision@1 |
| value: 0.749 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.27433333333333326 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.17060000000000003 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.0886 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.749 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.823 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.853 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.886 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.816961550160875 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.7949674603174605 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.7988750755190056 |
| name: Cosine Map@100 |
| --- |
| |
| # SentenceTransformer based on seregadgl/splade_gemma_google_base_checkpoint_100_clear |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [seregadgl/splade_gemma_google_base_checkpoint_100_clear](https://huggingface.co/seregadgl/splade_gemma_google_base_checkpoint_100_clear) on the [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) 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:** [seregadgl/splade_gemma_google_base_checkpoint_100_clear](https://huggingface.co/seregadgl/splade_gemma_google_base_checkpoint_100_clear) <!-- at revision 20c38a098901bc44c1031a7537d0e3bf0aa93063 --> |
| - **Maximum Sequence Length:** 512 tokens |
| - **Output Dimensionality:** 768 dimensions |
| - **Similarity Function:** Cosine Similarity |
| - **Training Dataset:** |
| - [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) |
| <!-- - **Language:** Unknown --> |
| <!-- - **License:** Unknown --> |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| SentenceTransformer( |
| (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'}) |
| (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}) |
| (2): SparseLayer( |
| (linear): Linear(in_features=768, out_features=262144, bias=True) |
| ) |
| ) |
| ``` |
|
|
| ## 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 SentenceTransformer |
| |
| # Download from the 🤗 Hub |
| model = SentenceTransformer("seregadgl/splade_gemma_google_base_checkpoint_100_ver2_checkpoint100") |
| # Run inference |
| sentences = [ |
| 'query: 1452634 santool jawa 300 cl', |
| 'document: 1452634 santool съемник для сальников jawa 300 cl', |
| 'document: 1453934 santool съемник для сальников jawa 300 cl', |
| ] |
| 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, 0.1749, 0.1724], |
| # [0.1749, 1.0000, 0.7309], |
| # [0.1724, 0.7309, 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 |
|
|
| #### Information Retrieval |
|
|
| * Dataset: `val_set_fine` |
| * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
| | Metric | Value | |
| |:--------------------|:----------| |
| | cosine_accuracy@1 | 0.749 | |
| | cosine_precision@1 | 0.749 | |
| | cosine_precision@3 | 0.2743 | |
| | cosine_precision@5 | 0.1706 | |
| | cosine_precision@10 | 0.0886 | |
| | cosine_recall@1 | 0.749 | |
| | cosine_recall@3 | 0.823 | |
| | cosine_recall@5 | 0.853 | |
| | cosine_recall@10 | 0.886 | |
| | **cosine_ndcg@10** | **0.817** | |
| | cosine_mrr@10 | 0.795 | |
| | cosine_map@100 | 0.7989 | |
| |
| <!-- |
| ## 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 |
| |
| #### car_and_product_triplet_103k |
| |
| * Dataset: [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) at [3519181](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k/tree/35191818e272dc373544bd86903a5146c6f993e2) |
| * Size: 102,127 training samples |
| * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | anchor | positive | negative | |
| |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| |
| | type | string | string | string | |
| | details | <ul><li>min: 5 tokens</li><li>mean: 16.27 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 23.62 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 23.2 tokens</li><li>max: 47 tokens</li></ul> | |
| * Samples: |
| | anchor | positive | negative | |
| |:--------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------| |
| | <code>query: погружной блендер tefal optichef hb64f810</code> | <code>document: погружной блендер тефаль optichef hb64f810</code> | <code>document: погружной миксер tefal mixchef hb64f850</code> | |
| | <code>query: 375675836 niteo</code> | <code>document: тосол 375675836 для ford f350 полуночный синий</code> | <code>document: тосол 375625836 для ford f350 полуночный синий фиалковый</code> | |
| | <code>query: накидка с подогревом dodge viper pink</code> | <code>document: накидка с подогревом acdelco арт 787327sx dodge viper розовый</code> | <code>document: 787327sx накидка с подогревом indian challenger лаймовый</code> | |
| * Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#spladeloss) with these parameters: |
| ```json |
| { |
| "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False)", |
| "document_regularizer_weight": 1e-05, |
| "query_regularizer_weight": 1e-05 |
| } |
| ``` |
| |
| ### Evaluation Dataset |
| |
| #### car_and_product_triplet_103k |
| |
| * Dataset: [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) at [3519181](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k/tree/35191818e272dc373544bd86903a5146c6f993e2) |
| * Size: 1,000 evaluation samples |
| * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | anchor | positive | negative | |
| |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | string | string | string | |
| | details | <ul><li>min: 5 tokens</li><li>mean: 16.73 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 23.54 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 22.66 tokens</li><li>max: 65 tokens</li></ul> | |
| * Samples: |
| | anchor | positive | negative | |
| |:------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | <code>query: зеркала для 'слепых' зон volkswagen arteon</code> | <code>document: зеркала для 'слепых' зон 86635985zz для volkswagen arteon перламутровочёрный</code> | <code>document: 86635985zz зеркала для 'слепых' зон иж юпитер2 голубой</code> | |
| | <code>query: elf bar lux 1500 лимонад голубой малины 1500 </code> | <code>document: одноразовая электронная сигарета эльф бар 1 5000 мл lemonade blue raspberry 340440526</code> | <code>document: elf bar vibe 1000 мохито зелёного яблока 1000</code> | |
| | <code>query: удалитель наклеек chevrolet corvette onyx</code> | <code>document: удалитель наклеек 20810588pl для chevrolet corvette оникс</code> | <code>document: удалитель наклеек 20810588pl для maserati levante янтарный</code> | |
| * Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#spladeloss) with these parameters: |
| ```json |
| { |
| "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False)", |
| "document_regularizer_weight": 1e-05, |
| "query_regularizer_weight": 1e-05 |
| } |
| ``` |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
| |
| - `eval_strategy`: steps |
| - `gradient_accumulation_steps`: 16 |
| - `learning_rate`: 0.0001 |
| - `num_train_epochs`: 1 |
| - `warmup_steps`: 10 |
| - `fp16`: True |
| - `load_best_model_at_end`: True |
| - `router_mapping`: {'query': 'anchor', 'document': 'positive'} |
|
|
| #### 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`: 16 |
| - `eval_accumulation_steps`: None |
| - `torch_empty_cache_steps`: None |
| - `learning_rate`: 0.0001 |
| - `weight_decay`: 0.0 |
| - `adam_beta1`: 0.9 |
| - `adam_beta2`: 0.999 |
| - `adam_epsilon`: 1e-08 |
| - `max_grad_norm`: 1.0 |
| - `num_train_epochs`: 1 |
| - `max_steps`: -1 |
| - `lr_scheduler_type`: linear |
| - `lr_scheduler_kwargs`: {} |
| - `warmup_ratio`: 0.0 |
| - `warmup_steps`: 10 |
| - `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 |
| - `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`: True |
| - `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} |
| - `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} |
| - `parallelism_config`: None |
| - `deepspeed`: None |
| - `label_smoothing_factor`: 0.0 |
| - `optim`: adamw_torch_fused |
| - `optim_args`: None |
| - `adafactor`: False |
| - `group_by_length`: False |
| - `length_column_name`: length |
| - `project`: huggingface |
| - `trackio_space_id`: trackio |
| - `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`: no |
| - `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`: True |
| - `prompts`: None |
| - `batch_sampler`: batch_sampler |
| - `multi_dataset_batch_sampler`: proportional |
| - `router_mapping`: {'query': 'anchor', 'document': 'positive'} |
| - `learning_rate_mapping`: {} |
|
|
| </details> |
|
|
| ### Training Logs |
| | Epoch | Step | Validation Loss | val_set_fine_cosine_ndcg@10 | |
| |:------:|:----:|:---------------:|:---------------------------:| |
| | 0.0125 | 10 | 0.8461 | 0.7841 | |
| | 0.0251 | 20 | 0.8195 | 0.8009 | |
| | 0.0376 | 30 | 0.7884 | 0.7967 | |
| | 0.0501 | 40 | 0.7641 | 0.8097 | |
| | 0.0627 | 50 | 0.7503 | 0.8146 | |
| | 0.0752 | 60 | 0.7140 | 0.8151 | |
| | 0.0877 | 70 | 0.7165 | 0.8180 | |
| | 0.1003 | 80 | 0.6955 | 0.8131 | |
| | 0.1128 | 90 | 0.6866 | 0.8157 | |
| | 0.1253 | 100 | 0.6735 | 0.8170 | |
|
|
|
|
| ### Framework Versions |
| - Python: 3.12.12 |
| - Sentence Transformers: 5.2.2 |
| - Transformers: 4.57.1 |
| - PyTorch: 2.8.0+cu126 |
| - Accelerate: 1.11.0 |
| - Datasets: 4.4.2 |
| - Tokenizers: 0.22.1 |
|
|
| ## 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{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} |
| } |
| ``` |
|
|
| #### 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.* |
| --> |
