Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,522 @@
+---
+base_model: silma-ai/silma-embeddding-matryoshka-0.1
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:34436
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: Three men are playing chess.
+  sentences:
+  - Two men are fighting.
+  - امرأة تحمل و تحمل طفل كنغر
+  - Two men are playing chess.
+- source_sentence: Two men are playing chess.
+  sentences:
+  - رجل يعزف على الغيتار و يغني
+  - Three men are playing chess.
+  - طائرة طيران تقلع
+- source_sentence: Two men are playing chess.
+  sentences:
+  - A man is playing a large flute. رجل يعزف على ناي كبير
+  - The man is playing the piano. الرجل يعزف على البيانو
+  - Three men are playing chess.
+- source_sentence: الرجل يعزف على البيانو The man is playing the piano.
+  sentences:
+  - رجل يجلس ويلعب الكمان A man seated is playing the cello.
+  - ثلاثة رجال يلعبون الشطرنج.
+  - الرجل يعزف على الغيتار The man is playing the guitar.
+- source_sentence: الرجل ضرب الرجل الآخر بعصا The man hit the other man with a stick.
+  sentences:
+  - الرجل صفع الرجل الآخر بعصا The man spanked the other man with a stick.
+  - A plane is taking off.
+  - A man is smoking. رجل يدخن
+model-index:
+- name: SentenceTransformer based on silma-ai/silma-embeddding-matryoshka-0.1
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8509127994264242
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8548500966032416
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.821303728669975
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8364598068079891
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8210450198328316
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8382181658285147
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8491261828772604
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8559811107036664
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8509127994264242
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8559811107036664
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8498025312190702
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8530609768738506
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8181745876468085
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8328727236454085
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8193792688284338
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8338632184708783
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8396368156921546
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8484397673758116
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8498025312190702
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8530609768738506
+      name: Spearman Max
+---
+
+# SentenceTransformer based on silma-ai/silma-embeddding-matryoshka-0.1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [silma-ai/silma-embeddding-matryoshka-0.1](https://huggingface.co/silma-ai/silma-embeddding-matryoshka-0.1). 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:** [silma-ai/silma-embeddding-matryoshka-0.1](https://huggingface.co/silma-ai/silma-embeddding-matryoshka-0.1) <!-- at revision 9eb50734f432656a01e1f88d28fa9a6fe8b9e148 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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:
+
+```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("silma-ai/silma-embeddding-sts-0.1")
+# Run inference
+sentences = [
+    'الرجل ضرب الرجل الآخر بعصا The man hit the other man with a stick.',
+    'الرجل صفع الرجل الآخر بعصا The man spanked the other man with a stick.',
+    'A man is smoking. رجل يدخن',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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
+
+#### Semantic Similarity
+* Dataset: `sts-dev-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8509     |
+| **spearman_cosine** | **0.8549** |
+| pearson_manhattan   | 0.8213     |
+| spearman_manhattan  | 0.8365     |
+| pearson_euclidean   | 0.821      |
+| spearman_euclidean  | 0.8382     |
+| pearson_dot         | 0.8491     |
+| spearman_dot        | 0.856      |
+| pearson_max         | 0.8509     |
+| spearman_max        | 0.856      |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8498     |
+| **spearman_cosine** | **0.8531** |
+| pearson_manhattan   | 0.8182     |
+| spearman_manhattan  | 0.8329     |
+| pearson_euclidean   | 0.8194     |
+| spearman_euclidean  | 0.8339     |
+| pearson_dot         | 0.8396     |
+| spearman_dot        | 0.8484     |
+| pearson_max         | 0.8498     |
+| spearman_max        | 0.8531     |
+
+<!--
+## 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: 34,436 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: 4 tokens</li><li>mean: 15.18 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.18 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                          | sentence2                                                                                          | score             |
+  |:---------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:------------------|
+  | <code>A woman picks up and holds a baby kangaroo in her arms. امرأة تحمل في ذراعها طفل كنغر</code> | <code>A woman picks up and holds a baby kangaroo. امرأة تحمل و تحمل طفل كنغر</code>                | <code>0.92</code> |
+  | <code>امرأة تحمل و تحمل طفل كنغر A woman picks up and holds a baby kangaroo.</code>                | <code>امرأة تحمل في ذراعها طفل كنغر A woman picks up and holds a baby kangaroo in her arms.</code> | <code>0.92</code> |
+  | <code>رجل يعزف على الناي</code>                                                                    | <code>رجل يعزف على فرقة الخيزران</code>                                                            | <code>0.77</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 100 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 100 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 15.96 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.96 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 0.1</li><li>mean: 0.72</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                           | sentence2                                | score            |
+  |:------------------------------------|:-----------------------------------------|:-----------------|
+  | <code>طائرة ستقلع</code>            | <code>طائرة طيران تقلع</code>            | <code>1.0</code> |
+  | <code>طائرة طيران تقلع</code>       | <code>طائرة ستقلع</code>                 | <code>1.0</code> |
+  | <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 250
+- `per_device_eval_batch_size`: 10
+- `learning_rate`: 1e-06
+- `num_train_epochs`: 10
+- `bf16`: True
+- `dataloader_drop_last`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### 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`: 250
+- `per_device_eval_batch_size`: 10
+- `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`: 1e-06
+- `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`: 0.0
+- `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`: True
+- `fp16`: False
+- `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`: True
+- `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_fused
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | sts-dev-512_spearman_cosine | sts-dev-256_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------:|:---------------------------:|
+| 0.3650 | 50   | 0.0395        | 0.0424          | 0.8486                      | 0.8487                      |
+| 0.7299 | 100  | 0.031         | 0.0427          | 0.8493                      | 0.8495                      |
+| 1.0949 | 150  | 0.0344        | 0.0430          | 0.8496                      | 0.8496                      |
+| 1.4599 | 200  | 0.0313        | 0.0427          | 0.8506                      | 0.8504                      |
+| 1.8248 | 250  | 0.0267        | 0.0428          | 0.8504                      | 0.8506                      |
+| 2.1898 | 300  | 0.0309        | 0.0429          | 0.8516                      | 0.8515                      |
+| 2.5547 | 350  | 0.0276        | 0.0425          | 0.8531                      | 0.8521                      |
+| 2.9197 | 400  | 0.028         | 0.0426          | 0.8530                      | 0.8515                      |
+| 3.2847 | 450  | 0.0281        | 0.0425          | 0.8539                      | 0.8521                      |
+| 3.6496 | 500  | 0.0248        | 0.0425          | 0.8542                      | 0.8523                      |
+| 4.0146 | 550  | 0.0302        | 0.0424          | 0.8541                      | 0.8520                      |
+| 4.3796 | 600  | 0.0261        | 0.0421          | 0.8545                      | 0.8523                      |
+| 4.7445 | 650  | 0.0233        | 0.0420          | 0.8544                      | 0.8522                      |
+| 5.1095 | 700  | 0.0281        | 0.0419          | 0.8547                      | 0.8528                      |
+| 5.4745 | 750  | 0.0257        | 0.0419          | 0.8546                      | 0.8531                      |
+| 5.8394 | 800  | 0.0235        | 0.0418          | 0.8546                      | 0.8527                      |
+| 6.2044 | 850  | 0.0268        | 0.0418          | 0.8551                      | 0.8529                      |
+| 6.5693 | 900  | 0.0238        | 0.0416          | 0.8552                      | 0.8526                      |
+| 6.9343 | 950  | 0.0255        | 0.0416          | 0.8549                      | 0.8526                      |
+| 7.2993 | 1000 | 0.0253        | 0.0416          | 0.8548                      | 0.8528                      |
+| 7.6642 | 1050 | 0.0225        | 0.0415          | 0.8550                      | 0.8525                      |
+| 8.0292 | 1100 | 0.0276        | 0.0414          | 0.8550                      | 0.8528                      |
+| 8.3942 | 1150 | 0.0244        | 0.0415          | 0.8550                      | 0.8533                      |
+| 8.7591 | 1200 | 0.0218        | 0.0414          | 0.8551                      | 0.8529                      |
+| 9.1241 | 1250 | 0.0263        | 0.0414          | 0.8550                      | 0.8531                      |
+| 9.4891 | 1300 | 0.0241        | 0.0414          | 0.8552                      | 0.8533                      |
+| 9.8540 | 1350 | 0.0227        | 0.0415          | 0.8549                      | 0.8531                      |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.2.0
+- Transformers: 4.45.2
+- PyTorch: 2.3.1
+- Accelerate: 1.0.1
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
+
+## 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",
+}
+```
+
+<!--
+## 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 +1,25 @@
+{
+  "_name_or_path": "/workspace/v3-nli_silma-ai-silma-embeddding-matryoshka-0.1-2024-10-13_16-54-06/final",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.45.2",
+    "pytorch": "2.3.1"
+  },
+  "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:d76b2a8eb38cc2c0710bcfb46b9b6a732480f6db36e7b858b8f466e5b615f539
+size 540795752

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "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 +1,93 @@
+{
+  "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
+    },
+    "5": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
+  "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]"
+}