Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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 +1,714 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:557850
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+datasets: []
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: ذكر متوازن بعناية يقف على قدم واحدة بالقرب من منطقة شاطئ المحيط
+    النظيفة
+  sentences:
+  - رجل يقدم عرضاً
+  - هناك رجل بالخارج قرب الشاطئ
+  - رجل يجلس على أريكه
+- source_sentence: رجل يقفز إلى سريره القذر
+  sentences:
+  - السرير قذر.
+  - رجل يضحك أثناء غسيل الملابس
+  - الرجل على القمر
+- source_sentence: الفتيات بالخارج
+  sentences:
+  - امرأة تلف الخيط إلى كرات بجانب كومة من الكرات
+  - فتيان يركبان في جولة متعة
+  - ثلاث فتيات يقفون سوية في غرفة واحدة تستمع وواحدة تكتب على الحائط والثالثة تتحدث
+    إليهن
+- source_sentence: الرجل يرتدي قميصاً أزرق.
+  sentences:
+  - رجل يرتدي قميصاً أزرق يميل إلى الجدار بجانب الطريق مع شاحنة زرقاء وسيارة حمراء
+    مع الماء في الخلفية.
+  - كتاب القصص مفتوح
+  - رجل يرتدي قميص أسود يعزف على الجيتار.
+- source_sentence: يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة
+    شابة.
+  sentences:
+  - ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه
+  - رجل يستلقي على وجهه على مقعد في الحديقة.
+  - الشاب نائم بينما الأم تقود ابنتها إلى الحديقة
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8538831619509135
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.861625750018802
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8496745674597512
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8513333417508545
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8516261261374778
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8540549341060195
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7281308266536204
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7230282720855726
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8538831619509135
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.861625750018802
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8542379189261009
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8609329396560859
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8486657899695456
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8512120732504748
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8505249483849495
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8538738365440234
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7075618032859148
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7028728329509918
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8542379189261009
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8609329396560859
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8486308733045101
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8578681811996274
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8404506123980291
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.845565163232125
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8414758099131773
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8471566121478254
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6668664182302968
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6651222481800894
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8486308733045101
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8578681811996274
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8389761445410956
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8499312736457453
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8287388421834582
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8353046807483782
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8297699263897746
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8371843253238523
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5855876200722326
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5834920267418124
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8389761445410956
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8499312736457453
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8290685425698586
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8429054799136109
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8100968316314205
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8221121550434057
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8129044863346081
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8255133471709527
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5067257944655903
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5109761436588146
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8290685425698586
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8429054799136109
+      name: Spearman Max
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the Omartificial-Intelligence-Space/arabic-n_li-triplet 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:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) <!-- at revision 79f2382ceacceacdf38563d7c5d16b9ff8d725d6 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - Omartificial-Intelligence-Space/arabic-n_li-triplet
+<!-- - **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': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (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("Omartificial-Intelligence-Space/paraphrase-multilingual-mpnet-base-v2-Arabic-nli-matryoshka")
+# Run inference
+sentences = [
+    'يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة شاب��.',
+    'ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه',
+    'الشاب نائم بينما الأم تقود ابنتها إلى الحديقة',
+]
+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-test-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8539     |
+| **spearman_cosine** | **0.8616** |
+| pearson_manhattan   | 0.8497     |
+| spearman_manhattan  | 0.8513     |
+| pearson_euclidean   | 0.8516     |
+| spearman_euclidean  | 0.8541     |
+| pearson_dot         | 0.7281     |
+| spearman_dot        | 0.723      |
+| pearson_max         | 0.8539     |
+| spearman_max        | 0.8616     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8542     |
+| **spearman_cosine** | **0.8609** |
+| pearson_manhattan   | 0.8487     |
+| spearman_manhattan  | 0.8512     |
+| pearson_euclidean   | 0.8505     |
+| spearman_euclidean  | 0.8539     |
+| pearson_dot         | 0.7076     |
+| spearman_dot        | 0.7029     |
+| pearson_max         | 0.8542     |
+| spearman_max        | 0.8609     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8486     |
+| **spearman_cosine** | **0.8579** |
+| pearson_manhattan   | 0.8405     |
+| spearman_manhattan  | 0.8456     |
+| pearson_euclidean   | 0.8415     |
+| spearman_euclidean  | 0.8472     |
+| pearson_dot         | 0.6669     |
+| spearman_dot        | 0.6651     |
+| pearson_max         | 0.8486     |
+| spearman_max        | 0.8579     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.839      |
+| **spearman_cosine** | **0.8499** |
+| pearson_manhattan   | 0.8287     |
+| spearman_manhattan  | 0.8353     |
+| pearson_euclidean   | 0.8298     |
+| spearman_euclidean  | 0.8372     |
+| pearson_dot         | 0.5856     |
+| spearman_dot        | 0.5835     |
+| pearson_max         | 0.839      |
+| spearman_max        | 0.8499     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8291     |
+| **spearman_cosine** | **0.8429** |
+| pearson_manhattan   | 0.8101     |
+| spearman_manhattan  | 0.8221     |
+| pearson_euclidean   | 0.8129     |
+| spearman_euclidean  | 0.8255     |
+| pearson_dot         | 0.5067     |
+| spearman_dot        | 0.511      |
+| pearson_max         | 0.8291     |
+| spearman_max        | 0.8429     |
+
+<!--
+## 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
+
+#### Omartificial-Intelligence-Space/arabic-n_li-triplet
+
+* Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
+* Size: 557,850 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: 10.33 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.21 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.32 tokens</li><li>max: 53 tokens</li></ul> |
+* Samples:
+  | anchor                                                      | positive                                    | negative                            |
+  |:------------------------------------------------------------|:--------------------------------------------|:------------------------------------|
+  | <code>شخص على حصان يقفز فوق طائرة معطلة</code>              | <code>شخص في الهواء الطلق، على حصان.</code> | <code>شخص في مطعم، يطلب عجة.</code> |
+  | <code>أطفال يبتسمون و يلوحون للكاميرا</code>                | <code>هناك أطفال حاضرون</code>              | <code>الاطفال يتجهمون</code>        |
+  | <code>صبي يقفز على لوح التزلج في منتصف الجسر الأحمر.</code> | <code>الفتى يقوم بخدعة التزلج</code>        | <code>الصبي يتزلج على الرصيف</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Omartificial-Intelligence-Space/arabic-n_li-triplet
+
+* Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
+* Size: 6,584 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: 21.86 tokens</li><li>max: 105 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.22 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.2 tokens</li><li>max: 33 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                               | positive                                               | negative                                           |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|:---------------------------------------------------|
+  | <code>امرأتان يتعانقان بينما يحملان حزمة</code>                                                                                                      | <code>إمرأتان يحملان حزمة</code>                       | <code>الرجال يتشاجرون خارج مطعم</code>             |
+  | <code>طفلين صغيرين يرتديان قميصاً أزرق، أحدهما يرتدي الرقم 9 والآخر يرتدي الرقم 2 يقفان على خطوات خشبية في الحمام ويغسلان أيديهما في المغسلة.</code> | <code>طفلين ي��تديان قميصاً مرقماً يغسلون أيديهم</code> | <code>طفلين يرتديان سترة يذهبان إلى المدرسة</code> |
+  | <code>رجل يبيع الدونات لعميل خلال معرض عالمي أقيم في مدينة أنجليس</code>                                                                             | <code>رجل يبيع الدونات لعميل</code>                    | <code>امرأة تشرب قهوتها في مقهى صغير</code>        |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_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`: 1
+- `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
+- `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, '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_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
+|:------:|:----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
+| 0.2294 | 500  | 10.1279       | -                            | -                            | -                            | -                           | -                            |
+| 0.4587 | 1000 | 8.0384        | -                            | -                            | -                            | -                           | -                            |
+| 0.6881 | 1500 | 7.3484        | -                            | -                            | -                            | -                           | -                            |
+| 0.9174 | 2000 | 4.2216        | -                            | -                            | -                            | -                           | -                            |
+| 1.0    | 2180 | -             | 0.8499                       | 0.8579                       | 0.8609                       | 0.8429                      | 0.8616                       |
+
+
+### Framework Versions
+- Python: 3.9.18
+- Sentence Transformers: 3.0.1
+- Transformers: 4.40.0
+- PyTorch: 2.2.2+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.19.0
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```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}
+}
+```
+
+<!--
+## 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 +1,29 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.40.0",
+    "pytorch": "2.2.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94499f2ede1a5584f59396bc6865f0b8a2ecfcb7ecc6e27c8b1ebe8005e5cff4
+size 1112197096

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": 128,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}