End of training

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 312,
+  "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
+}

README.md

@@ -1,3 +1,608 @@
 ---
-license: mit
+base_model: cointegrated/rubert-tiny2
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:13690
+- loss:ContrastiveLoss
+widget:
+- source_sentence: Грузоблочный тренажер Bronze Gym D-015 - жим ногами в Москве Силовые
+    тренажеры Грузоблочные Bronze Gym D-015 - жим ногами
+  sentences:
+  - Трицепс-машина Matrix G3-S45 Главная Силовые тренажеры Трицепс-машина Matrix G3-S45
+  - Верхняя тяга Iron Bull IR-TE08 nan Силовые тренажеры Грузоблочные тренажеры
+  - Горизонтальный велоэргометр Matrix Lifestyle с консолью LED nan Велотренажеры
+    Matrix
+- source_sentence: Эллиптический тренажер Precor EFX 731 nan Эллиптические тренажеры
+    Precor
+  sentences:
+  - Беговая дорожка коммерческая AeroFit X3-T 10″LCD в Москве Кардиотренажеры Беговые
+    дорожки AeroFit X3-T 10″LCD
+  - Машина Смита Matrix G1-FW161 Главная Силовые тренажеры Машина Смита Matrix G1-FW161
+  - Эллиптический тренажер CardioPower X75 Главная Эллиптические тренажеры Бренды
+- source_sentence: Велотренажер Clear Fit Envy CFB 45 Ego Главная Велотренажеры Бренды
+  sentences:
+  - Велотренажер Spirit Fitness MU100 реабилитационный в Москве Кардиотренажеры Велотренажеры
+    Spirit Fitness MU100 реабилитационный
+  - Многофункциональная блочная станция Teca SP785C Две Гребных тяги nan Силовые тренажеры
+    Мультистанции
+  - Беговая дорожка Sports Art T670 Главная Беговые дорожки Бренды
+- source_sentence: Горизонтальный велотренажер TRUE C400 Главная Велотренажеры Бренды
+  sentences:
+  - Велотренажер UltraGym UG-B002 nan Велотренажеры UltraGym
+  - Грузоблочный тренажер Precor DSL505 - задние дельты/баттерфляй в Москве Силовые
+    тренажеры Грузоблочные Precor DSL505 - задние дельты/баттерфляй
+  - Беговая дорожка Hasttings LCT80 Беговые дорожки Hasttings Hasttings LCT80
+- source_sentence: Беговая дорожка Hasttings CT100 Главная Беговые дорожки Беговая
+    дорожка Hasttings CT100
+  sentences:
+  - Вертикальная тяга RangeMax CST-018 nan Силовые тренажеры Грузоблочные тренажеры
+  - Беговая дорожка ProForm 910 Беговые дорожки ProForm ProForm 910
+  - Беговая дорожка AMMITY SPACE ATM 5000 Главная Беговые дорожки Бренды
+model-index:
+- name: SentenceTransformer based on cointegrated/rubert-tiny2
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: cv
+      type: cv
+    metrics:
+    - type: cosine_accuracy
+      value: 1.0
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7240798473358154
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 1.0
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7240798473358154
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 1.0
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 1.0
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 1.0
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 1.0
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.7240797877311707
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 1.0
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.7240797877311707
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 1.0
+      name: Dot Precision
+    - type: dot_recall
+      value: 1.0
+      name: Dot Recall
+    - type: dot_ap
+      value: 1.0
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 1.0
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 9.055404663085938
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 1.0
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 9.055404663085938
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 1.0
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 1.0
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 1.0
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 1.0
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.6519391536712646
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 1.0
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.6519391536712646
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 1.0
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 1.0
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 1.0
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 1.0
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 9.055404663085938
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 1.0
+      name: Max F1
+    - type: max_f1_threshold
+      value: 9.055404663085938
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 1.0
+      name: Max Precision
+    - type: max_recall
+      value: 1.0
+      name: Max Recall
+    - type: max_ap
+      value: 1.0
+      name: Max Ap
 ---
+
+# SentenceTransformer based on cointegrated/rubert-tiny2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2). It maps sentences & paragraphs to a 312-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:** [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) <!-- at revision dad72b8f77c5eef6995dd3e4691b758ba56b90c3 -->
+- **Maximum Sequence Length:** 2048 tokens
+- **Output Dimensionality:** 312 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/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': 2048, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 312, '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): Normalize()
+)
+```
+
+## 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Беговая дорожка Hasttings CT100 Главная Беговые дорожки Беговая дорожка Hasttings CT100',
+    'Беговая дорожка AMMITY SPACE ATM 5000 Главная Беговые дорожки Бренды',
+    'Беговая дорожка ProForm 910 Беговые дорожки ProForm ProForm 910',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 312]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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
+
+#### Binary Classification
+* Dataset: `cv`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value   |
+|:-----------------------------|:--------|
+| cosine_accuracy              | 1.0     |
+| cosine_accuracy_threshold    | 0.7241  |
+| cosine_f1                    | 1.0     |
+| cosine_f1_threshold          | 0.7241  |
+| cosine_precision             | 1.0     |
+| cosine_recall                | 1.0     |
+| cosine_ap                    | 1.0     |
+| dot_accuracy                 | 1.0     |
+| dot_accuracy_threshold       | 0.7241  |
+| dot_f1                       | 1.0     |
+| dot_f1_threshold             | 0.7241  |
+| dot_precision                | 1.0     |
+| dot_recall                   | 1.0     |
+| dot_ap                       | 1.0     |
+| manhattan_accuracy           | 1.0     |
+| manhattan_accuracy_threshold | 9.0554  |
+| manhattan_f1                 | 1.0     |
+| manhattan_f1_threshold       | 9.0554  |
+| manhattan_precision          | 1.0     |
+| manhattan_recall             | 1.0     |
+| manhattan_ap                 | 1.0     |
+| euclidean_accuracy           | 1.0     |
+| euclidean_accuracy_threshold | 0.6519  |
+| euclidean_f1                 | 1.0     |
+| euclidean_f1_threshold       | 0.6519  |
+| euclidean_precision          | 1.0     |
+| euclidean_recall             | 1.0     |
+| euclidean_ap                 | 1.0     |
+| max_accuracy                 | 1.0     |
+| max_accuracy_threshold       | 9.0554  |
+| max_f1                       | 1.0     |
+| max_f1_threshold             | 9.0554  |
+| max_precision                | 1.0     |
+| max_recall                   | 1.0     |
+| **max_ap**                   | **1.0** |
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+
+* Size: 13,690 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          | score                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                          |
+  | details | <ul><li>min: 14 tokens</li><li>mean: 29.13 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 29.18 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.51</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                       | sentence2                                                                                                                      | score            |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Велотренажер аэродинамический Spirit Fitness AB900+ Air Bike в Москве Кардиотренажеры Велотренажеры Spirit Fitness AB900+ Air Bike</code> | <code>Велотренажер IZHIMIO СL 1500 Главная Велотренажеры Бренды</code>                                                         | <code>1.0</code> |
+  | <code>Эллиптический тренажер Sports Art E835 Главная Эллиптические тренажеры Бренды</code>                                                      | <code>Степпер Matrix C7XI в Мо��кве Кардиотренажеры Степперы Matrix C7XI</code>                                                 | <code>0.0</code> |
+  | <code>Мультистанция Nohrd SlimBeam nan Силовые тренажеры Мультистанции</code>                                                                   | <code>Эллиптический тренажер Koenigsmann JX-170EF в Москве Кардиотренажеры Эллиптические тренажеры Koenigsmann JX-170EF</code> | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 28 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 28 samples:
+  |         | sentence1                                                                          | sentence2                                                                         | score                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            | float                                                          |
+  | details | <ul><li>min: 15 tokens</li><li>mean: 27.18 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 28.0 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.61</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                              | sentence2                                                                                    | score            |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Беговая дорожка Carbon Yukon Беговые дорожки Carbon Carbon Yukon</code>                                                                          | <code>Беговая дорожка Hasttings LCT80 Беговые дорожки Hasttings Hasttings LCT80</code>       | <code>1.0</code> |
+  | <code>Беговая дорожка Беговая дорожка DFC BOSS I T-B1 для реабилитации Беговые дорожки DFC Беговая дорожка DFC BOSS I T-B1 для реабилитации</code>     | <code>Беговая дорожка EVO FITNESS Cosmo 5 Главная Беговые дорожки Бренды</code>              | <code>1.0</code> |
+  | <code>Грузоблочный тренажер Precor C010ES - жим ногами/икроножные в Москве Силовые тренажеры Грузоблочные Precor C010ES - жим ногами/икроножные</code> | <code>Кроссовер Bronze Gym D-005 Главная Силовые тренажеры Кроссовер Bronze Gym D-005</code> | <code>1.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 10
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `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`: 10
+- `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}
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `dispatch_batches`: None
+- `split_batches`: 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
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | cv_max_ap |
+|:------:|:----:|:-------------:|:------:|:---------:|
+| 0      | 0    | -             | -      | 0.7655    |
+| 1.0    | 428  | -             | 0.0056 | 1.0       |
+| 1.1682 | 500  | 0.0078        | -      | -         |
+| 2.0    | 856  | -             | 0.0015 | 1.0       |
+| 2.3364 | 1000 | 0.0019        | -      | -         |
+| 3.0    | 1284 | -             | 0.0011 | 1.0       |
+| 3.5047 | 1500 | 0.0013        | -      | -         |
+| 4.0    | 1712 | -             | 0.0007 | 1.0       |
+| 4.6729 | 2000 | 0.001         | -      | -         |
+| 5.0    | 2140 | -             | 0.0004 | 1.0       |
+| 5.8411 | 2500 | 0.0008        | -      | -         |
+| 6.0    | 2568 | -             | 0.0002 | 1.0       |
+| 7.0    | 2996 | -             | 0.0002 | 1.0       |
+| 7.0093 | 3000 | 0.0007        | -      | -         |
+| 8.0    | 3424 | -             | 0.0001 | 1.0       |
+| 8.1776 | 3500 | 0.0006        | -      | -         |
+| 9.0    | 3852 | -             | 0.0001 | 1.0       |
+| 9.3458 | 4000 | 0.0005        | -      | -         |
+| 10.0   | 4280 | -             | 0.0001 | 1.0       |
+
+
+### Framework Versions
+- Python: 3.11.8
+- Sentence Transformers: 3.1.0
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu118
+- Accelerate: 0.34.2
+- Datasets: 3.0.0
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.0",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1+cu118"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2144e003080b94faa1a4d12c252bc4ef9ce8a0ef9ee5aa0703fe5f1802087918
+size 116781184

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 2048,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c254543bedb8797d16298576c9ddb0d60c9a824f6facea1dcf4e174f6bacd80
+size 5496