Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ 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
+sts-multilingual-mpnet-base-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+sts-multilingual-mpnet-base-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+sts-multilingual-mpnet-base-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+sts-multilingual-mpnet-base-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+sts-multilingual-mpnet-base-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+sts-multilingual-mpnet-base-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+sts-multilingual-mpnet-base-v2.bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,781 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- mteb
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:AnglELoss
+- autoquant
+- gguf
+base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+widget:
+- source_sentence: 有些人在路上溜达。
+  sentences:
+  - Folk går
+  - Otururken gitar çalan adam.
+  - ארה"ב קבעה שסוריה השתמשה בנשק כימי
+- source_sentence: 緬甸以前稱為緬甸。
+  sentences:
+  - 缅甸以前叫缅甸。
+  - This is very contradictory.
+  - 한 남자가 아기를 안고 의자에 앉아 잠들어 있다.
+- source_sentence: אדם כותב.
+  sentences:
+  - האדם כותב.
+  - questa non è una risposta.
+  - 7 שוטרים נהרגו ו-4 שוטרים נפצעו.
+- source_sentence: הם מפחדים.
+  sentences:
+  - liên quan đến rủi ro đáng kể;
+  - A man is playing a guitar.
+  - A man is playing a piano.
+- source_sentence: 一个女人正在洗澡。
+  sentences:
+  - A woman is taking a bath.
+  - En jente børster håret sitt
+  - אדם מחלק תפוח אדמה.
+pipeline_tag: sentence-similarity
+model-index:
+- name: Gameselo/STS-multilingual-mpnet-base-v2
+  results:
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: it
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6847049462613332
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: es
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6620948502618977
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: fr
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.7875616631597785
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: pl-en
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.7510805416538202
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: ar
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6265329479575293
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: pl
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.4335552432730643
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: de
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.5774252131250034
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: tr
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6383757017928495
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: es-it
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6624635951676386
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: ru
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.5866853707548388
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: en
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6385354535483773
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: zh-en
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6537294853166558
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: zh
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.6319430830291571
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: fr-pl
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.8451542547285167
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: de-fr
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.5798716781400349
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: es-en
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.7518021273920814
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: de-en
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.5749790581441845
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS22
+      type: mteb/sts22-crosslingual-sts
+      config: de-pl
+      split: test
+      revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+    metrics:
+    - type: cosine_spearman
+      value: 0.44220332625465214
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STSBenchmark
+      type: mteb/stsbenchmark-sts
+      config: default
+      split: test
+      revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
+    metrics:
+    - type: cosine_spearman
+      value: 0.9762486352335524
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: en-tr
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.7987027653005363
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: ko-ko
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.9766336939338607
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: fr-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.9067607122592818
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: en-ar
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.7703365842088069
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: nl-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.9114826394926738
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: it-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.9246785886944904
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: ar-ar
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.8124393788492182
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: es-es
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.872701191632785
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: en-de
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.9109414091487618
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: es-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.8553203530552356
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS17
+      type: mteb/sts17-crosslingual-sts
+      config: en-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: cosine_spearman
+      value: 0.9378741534997558
+---
+
+## State-of-the-Art Results Comparison (MTEB STS Multilingual Leaderboard)
+
+| Dataset           | State-of-the-art (Multi) | STSb-XLM-RoBERTa-base |    STS Multilingual MPNet base v2    |
+|-------------------|--------------------------|-----------------------|--------------------------------------|
+| Average           | 73.17                    | 71.68                 | **73.89**                            |
+| STS17 (ar-ar)     | **81.87**                | 80.43                 | 81.24                                |
+| STS17 (en-ar)     | **81.22**                | 76.3                  | 77.03                                |
+| STS17 (en-de)     | 87.3                     | 91.06                 | **91.09**                            |
+| STS17 (en-tr)     | 77.18                    | **80.74**             | 79.87                                |
+| STS17 (es-en)     | **88.24**                | 83.09                 | 85.53                                |
+| STS17 (es-es)     | **88.25**                | 84.16                 | 87.27                                |
+| STS17 (fr-en)     | 88.06                    | **91.33**             | 90.68                                |
+| STS17 (it-en)     | 89.68                    | **92.87**             | 92.47                                |
+| STS17 (ko-ko)     | 83.69                    | **97.67**             | 97.66                                |
+| STS17 (nl-en)     | 88.25                    | **92.13**             | 91.15                                |
+| STS22 (ar)        | 58.67                    | 58.67                 | **62.66**                            |
+| STS22 (de)        | **60.12**                | 52.17                 | 57.74                                |
+| STS22 (de-en)     | **60.92**                | 58.5                  | 57.5                                 |
+| STS22 (de-fr)     | **67.79**                | 51.28                 | 57.99                                |
+| STS22 (de-pl)     | **58.69**                | 44.56                 | 44.22                                |
+| STS22 (es)        | **68.57**                | 63.68                 | 66.21                                |
+| STS22 (es-en)     | **78.8**                 | 70.65                 | 75.18                                |
+| STS22 (es-it)     | **75.04**                | 60.88                 | 66.25                                |
+| STS22 (fr)        | **83.75**                | 76.46                 | 78.76                                |
+| STS22 (fr-pl)     | 84.52                    | 84.52                 | **84.52**                            |
+| STS22 (it)        | **79.28**                | 66.73                 | 68.47                                |
+| STS22 (pl)        | 42.08                    | 41.18                 | **43.36**                            |
+| STS22 (pl-en)     | **77.5**                 | 64.35                 | 75.11                                |
+| STS22 (ru)        | **61.71**                | 58.59                 | 58.67                                |
+| STS22 (tr)        | **68.72**                | 57.52                 | 63.84                                |
+| STS22 (zh-en)     | **71.88**                | 60.69                 | 65.37                                |
+| STSb              | 89.86                    | 95.05                 | **95.15**                            |
+
+**Bold** indicates the best result in each row.
+
+# 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). 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:** 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': 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("Gameselo/STS-multilingual-mpnet-base-v2")
+# Run inference
+sentences = [
+    '一个女人正在洗澡。',
+    'A woman is taking a bath.',
+    'En jente børster håret sitt',
+]
+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`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9551     |
+| **spearman_cosine** | **0.9593** |
+| pearson_manhattan   | 0.927      |
+| spearman_manhattan  | 0.9383     |
+| pearson_euclidean   | 0.9278     |
+| spearman_euclidean  | 0.9394     |
+| pearson_dot         | 0.876      |
+| spearman_dot        | 0.8865     |
+| pearson_max         | 0.9551     |
+| spearman_max        | 0.9593     |
+
+#### Evalutation results vs SOTA results
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.948      |
+| **spearman_cosine** | **0.9515** |
+| pearson_manhattan   | 0.9252     |
+| spearman_manhattan  | 0.9352     |
+| pearson_euclidean   | 0.9258     |
+| spearman_euclidean  | 0.9364     |
+| pearson_dot         | 0.8443     |
+| spearman_dot        | 0.8435     |
+| pearson_max         | 0.948      |
+| spearman_max        | 0.9515     |
+
+<!--
+## 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: 226,547 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                         | label                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                            |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 20.05 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 19.94 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 1.92</li><li>max: 398.6</li></ul> |
+* Samples:
+  | sentence_0                                                         | sentence_1                                                      | label                            |
+  |:-------------------------------------------------------------------|:----------------------------------------------------------------|:---------------------------------|
+  | <code>Bir kadın makineye dikiş dikiyor.</code>                     | <code>Bir kadın biraz et ekiyor.</code>                         | <code>0.12</code>                |
+  | <code>Snowden 'gegeven vluchtelingendocument door Ecuador'.</code> | <code>Snowden staat op het punt om uit Moskou te vliegen</code> | <code>0.24000000953674316</code> |
+  | <code>Czarny pies idzie mostem przez wodę</code>                   | <code>Czarny pies nie idzie mostem przez wodę</code>            | <code>0.74000000954</code>       |
+* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_angle_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `num_train_epochs`: 10
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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
+- `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
+- `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`: 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`: 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`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:-----------------------:|:------------------------:|
+| 0.5650 | 500  | 10.9426       | -                       | -                        |
+| 1.0    | 885  | -             | 0.9202                  | -                        |
+| 1.1299 | 1000 | 9.7184        | -                       | -                        |
+| 1.6949 | 1500 | 9.5348        | -                       | -                        |
+| 2.0    | 1770 | -             | 0.9400                  | -                        |
+| 2.2599 | 2000 | 9.4412        | -                       | -                        |
+| 2.8249 | 2500 | 9.3097        | -                       | -                        |
+| 3.0    | 2655 | -             | 0.9489                  | -                        |
+| 3.3898 | 3000 | 9.2357        | -                       | -                        |
+| 3.9548 | 3500 | 9.1594        | -                       | -                        |
+| 4.0    | 3540 | -             | 0.9528                  | -                        |
+| 4.5198 | 4000 | 9.0963        | -                       | -                        |
+| 5.0    | 4425 | -             | 0.9553                  | -                        |
+| 5.0847 | 4500 | 9.0382        | -                       | -                        |
+| 5.6497 | 5000 | 8.9837        | -                       | -                        |
+| 6.0    | 5310 | -             | 0.9567                  | -                        |
+| 6.2147 | 5500 | 8.9403        | -                       | -                        |
+| 6.7797 | 6000 | 8.8841        | -                       | -                        |
+| 7.0    | 6195 | -             | 0.9581                  | -                        |
+| 7.3446 | 6500 | 8.8513        | -                       | -                        |
+| 7.9096 | 7000 | 8.81          | -                       | -                        |
+| 8.0    | 7080 | -             | 0.9582                  | -                        |
+| 8.4746 | 7500 | 8.8069        | -                       | -                        |
+| 9.0    | 7965 | -             | 0.9589                  | -                        |
+| 9.0395 | 8000 | 8.7616        | -                       | -                        |
+| 9.6045 | 8500 | 8.7521        | -                       | -                        |
+| 10.0   | 8850 | -             | 0.9593                  | 0.6266                   |
+
+
+### Framework Versions
+- Python: 3.9.7
+- Sentence Transformers: 3.0.0
+- Transformers: 4.40.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.29.3
+- 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",
+}
+```
+
+#### AnglELoss
+```bibtex
+@misc{li2023angleoptimized,
+    title={AnglE-optimized Text Embeddings}, 
+    author={Xianming Li and Jing Li},
+    year={2023},
+    eprint={2309.12871},
+    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.*
+-->

sts-multilingual-mpnet-base-v2.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d51123062246c211623dc192a22139b2b47c0a31c88544342a04040d87c69f
+size 198577088

sts-multilingual-mpnet-base-v2.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f24fe8f17d8aa13b38fdfe3cbe256a81a8386ee5c856e73b21587e7325de33
+size 208677824

sts-multilingual-mpnet-base-v2.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8f572368b5cbd3431211301c9f8f2d22d4ee118eea6e1adba5fce3f733d9f3
+size 218732480

sts-multilingual-mpnet-base-v2.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d720cd704b59dd8208b3aa72b32bf044f6a1af6aed468b62d72e5ae8c2f4c1
+size 227137472

sts-multilingual-mpnet-base-v2.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e803d82b7da897feca2564d0c7479b5138fa0c48923b639100e5c3b6e4895cb
+size 236067776

sts-multilingual-mpnet-base-v2.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14500c6efe5444f3c49872490073474d2c40e68d69f8b58071e4b1c14a748c8
+size 303138240

sts-multilingual-mpnet-base-v2.bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f861fafd5e8fd6a500d6650ff0c0c2800bbe6de9d62a972381ca58cd88a021
+size 562765920