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": 1024,
+  "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 +1,985 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:1K<n<10K
+- loss:MatryoshkaLoss
+- loss:CoSENTLoss
+base_model: intfloat/multilingual-e5-large
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: El hombre captura una pelota
+  sentences:
+  - Un hombre lanza una pelota en el aire.
+  - Un hombre se encuentra tocando una flauta de madera.
+  - La mujer está maquillándose usando sombra de ojos.
+- source_sentence: Un hombre está buscando algo.
+  sentences:
+  - En un mercado de granjeros, se encuentra un hombre.
+  - Se acerca a la pista un avión suizo de color blanco.
+  - dos chicas jóvenes se abrazan en la hierba.
+- source_sentence: El avión está tocando tierra.
+  sentences:
+  - El avión animado se encuentra en proceso de aterrizaje.
+  - La capital de Siria fue golpeada por dos explosiones
+  - Violentos incidentes afectan a estudiantes chinos en Francia
+- source_sentence: Un hombre saltando la cuerda.
+  sentences:
+  - Un hombre está saltando la cuerda.
+  - Una mujer entrena a su perro para saltar en el aire.
+  - Los gatitos están comiendo de los platos.
+- source_sentence: tres perros gruñendo entre sí
+  sentences:
+  - Dos perros se aproximan uno al otro en el pasto.
+  - Una mujer sonriente brinda cariño a un pequeño bebé.
+  - Una mujer está montando a caballo en el campo.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-large
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8279951103268512
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8342643795984531
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8228439538329566
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.834870903153992
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8231076969394738
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8349270059177344
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8196281042113861
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8248683461954115
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8279951103268512
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8349270059177344
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8236357426336446
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8332692872015282
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8217552769156274
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8331746060276878
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8217859136681092
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8334069456110773
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8101789790612713
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8179205607773823
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8236357426336446
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8334069456110773
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.816222860848086
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8303708513421737
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8178715987143794
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8301047046554985
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8183826652089494
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8301804247624904
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7878741921967743
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7904844114269662
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8183826652089494
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8303708513421737
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.794202606017138
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8198385906414491
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8088714046889546
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8222921243120748
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8092312345267045
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8220266161646009
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7341586721030032
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7351749794310246
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8092312345267045
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8222921243120748
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.7727295051414095
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8076629783565549
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7976419723073269
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8147883308842346
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7979124462870892
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8123832197697319
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6725844492342726
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6673162832940408
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7979124462870892
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8147883308842346
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8630482725201897
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8813284718659181
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8770818288812614
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8810971983428288
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8770132070253477
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8812162173545179
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8581811981775829
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8707402246720045
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8770818288812614
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8813284718659181
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8589909139210625
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8799604919891442
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8744468387217347
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8791142262015441
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8747974723064821
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8795698184784307
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8464185524060444
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8549652098582826
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8747974723064821
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8799604919891442
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8528262537030415
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8762917275750132
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8715060008387856
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8780718380107112
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.87251419758469
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8788770265821976
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.801980870958869
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8007112694661982
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.87251419758469
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8788770265821976
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8392066286150661
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8692426944903685
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8631603748425567
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8715673768304316
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8643871758114816
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8724091426441261
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7461565194503229
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7403017354497338
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8643871758114816
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8724091426441261
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8213671607347727
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8621003145087452
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8530869243121955
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8631973638935834
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.854140567169475
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8632627342101252
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6853599968011839
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6726454086764928
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.854140567169475
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8632627342101252
+      name: Spearman Max
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on the clibrain/stsb_multi_es_aug_gpt3.5-turbo_2 dataset. It maps sentences & paragraphs to a 1024-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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
+<!-- - **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: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): 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("mrm8488/multilingual-e5-large-ft-sts-spanish-matryoshka-768-64-5e")
+# Run inference
+sentences = [
+    'tres perros gruñendo entre sí',
+    'Dos perros se aproximan uno al otro en el pasto.',
+    'Una mujer sonriente brinda cariño a un pequeño bebé.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.828      |
+| **spearman_cosine** | **0.8343** |
+| pearson_manhattan   | 0.8228     |
+| spearman_manhattan  | 0.8349     |
+| pearson_euclidean   | 0.8231     |
+| spearman_euclidean  | 0.8349     |
+| pearson_dot         | 0.8196     |
+| spearman_dot        | 0.8249     |
+| pearson_max         | 0.828      |
+| spearman_max        | 0.8349     |
+
+#### 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      | 0.8236     |
+| **spearman_cosine** | **0.8333** |
+| pearson_manhattan   | 0.8218     |
+| spearman_manhattan  | 0.8332     |
+| pearson_euclidean   | 0.8218     |
+| spearman_euclidean  | 0.8334     |
+| pearson_dot         | 0.8102     |
+| spearman_dot        | 0.8179     |
+| pearson_max         | 0.8236     |
+| spearman_max        | 0.8334     |
+
+#### 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      | 0.8162     |
+| **spearman_cosine** | **0.8304** |
+| pearson_manhattan   | 0.8179     |
+| spearman_manhattan  | 0.8301     |
+| pearson_euclidean   | 0.8184     |
+| spearman_euclidean  | 0.8302     |
+| pearson_dot         | 0.7879     |
+| spearman_dot        | 0.7905     |
+| pearson_max         | 0.8184     |
+| spearman_max        | 0.8304     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7942     |
+| **spearman_cosine** | **0.8198** |
+| pearson_manhattan   | 0.8089     |
+| spearman_manhattan  | 0.8223     |
+| pearson_euclidean   | 0.8092     |
+| spearman_euclidean  | 0.822      |
+| pearson_dot         | 0.7342     |
+| spearman_dot        | 0.7352     |
+| pearson_max         | 0.8092     |
+| spearman_max        | 0.8223     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7727     |
+| **spearman_cosine** | **0.8077** |
+| pearson_manhattan   | 0.7976     |
+| spearman_manhattan  | 0.8148     |
+| pearson_euclidean   | 0.7979     |
+| spearman_euclidean  | 0.8124     |
+| pearson_dot         | 0.6726     |
+| spearman_dot        | 0.6673     |
+| pearson_max         | 0.7979     |
+| spearman_max        | 0.8148     |
+
+#### 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      | 0.863      |
+| **spearman_cosine** | **0.8813** |
+| pearson_manhattan   | 0.8771     |
+| spearman_manhattan  | 0.8811     |
+| pearson_euclidean   | 0.877      |
+| spearman_euclidean  | 0.8812     |
+| pearson_dot         | 0.8582     |
+| spearman_dot        | 0.8707     |
+| pearson_max         | 0.8771     |
+| spearman_max        | 0.8813     |
+
+#### 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      | 0.859    |
+| **spearman_cosine** | **0.88** |
+| pearson_manhattan   | 0.8744   |
+| spearman_manhattan  | 0.8791   |
+| pearson_euclidean   | 0.8748   |
+| spearman_euclidean  | 0.8796   |
+| pearson_dot         | 0.8464   |
+| spearman_dot        | 0.855    |
+| pearson_max         | 0.8748   |
+| spearman_max        | 0.88     |
+
+#### 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      | 0.8528     |
+| **spearman_cosine** | **0.8763** |
+| pearson_manhattan   | 0.8715     |
+| spearman_manhattan  | 0.8781     |
+| pearson_euclidean   | 0.8725     |
+| spearman_euclidean  | 0.8789     |
+| pearson_dot         | 0.802      |
+| spearman_dot        | 0.8007     |
+| pearson_max         | 0.8725     |
+| spearman_max        | 0.8789     |
+
+#### 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      | 0.8392     |
+| **spearman_cosine** | **0.8692** |
+| pearson_manhattan   | 0.8632     |
+| spearman_manhattan  | 0.8716     |
+| pearson_euclidean   | 0.8644     |
+| spearman_euclidean  | 0.8724     |
+| pearson_dot         | 0.7462     |
+| spearman_dot        | 0.7403     |
+| pearson_max         | 0.8644     |
+| spearman_max        | 0.8724     |
+
+#### 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      | 0.8214     |
+| **spearman_cosine** | **0.8621** |
+| pearson_manhattan   | 0.8531     |
+| spearman_manhattan  | 0.8632     |
+| pearson_euclidean   | 0.8541     |
+| spearman_euclidean  | 0.8633     |
+| pearson_dot         | 0.6854     |
+| spearman_dot        | 0.6726     |
+| pearson_max         | 0.8541     |
+| spearman_max        | 0.8633     |
+
+<!--
+## 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
+
+#### clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
+
+* Dataset: clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
+* Size: 2,697 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: 8 tokens</li><li>mean: 22.25 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 22.01 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.67</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                                                             | sentence2                                                                                                    | score                          |
+  |:------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------|
+  | <code>El pájaro de tamaño reducido se posó con delicadeza en una rama cubierta de escarcha.</code>    | <code>Un ave de color amarillo descansaba tranquilamente en una rama.</code>                                 | <code>3.200000047683716</code> |
+  | <code>Una chica está tocando la flauta en un parque.</code>                                           | <code>Un grupo de músicos está tocando en un escenario al aire libre.</code>                                 | <code>1.286</code>             |
+  | <code>La aclamada escritora británica, Doris Lessing, galardonada con el premio Nobel, fallece</code> | <code>La destacada autora británica, Doris Lessing, reconocida con el prestigioso Premio Nobel, muere</code> | <code>4.199999809265137</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CoSENTLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
+
+* Dataset: clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
+* Size: 697 evaluation 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: 8 tokens</li><li>mean: 22.76 tokens</li><li>max: 67 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 22.26 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.3</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                           | sentence2                                                                                                                                                     | score                          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------|
+  | <code>Un incendio ocurrido en un hospital psiquiátrico ruso resultó en la trágica muerte de 38 personas.</code>                                                     | <code>Se teme que el incendio en un hospital psiquiátrico ruso cause la pérdida de la vida de 38 individuos.</code>                                           | <code>4.199999809265137</code> |
+  | <code>"Street dijo que el otro individuo a veces se siente avergonzado de su fiesta, lo cual provoca risas en la multitud"</code>                                   | <code>"A veces, el otro tipo se encuentra avergonzado de su fiesta y no se le puede culpar."</code>                                                           | <code>3.5</code>               |
+  | <code>El veterano diplomático de Malasia tuvo un encuentro con Suu Kyi el miércoles en la casa del lago en Yangon donde permanece bajo arresto domiciliario.</code> | <code>Razali Ismail tuvo una reunión de 90 minutos con Suu Kyi, quien ganó el Premio Nobel de la Paz en 1991, en su casa del lago donde está recluida.</code> | <code>3.691999912261963</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CoSENTLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### 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`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 5
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss    | sts-dev-128_spearman_cosine | sts-dev-256_spearman_cosine | sts-dev-512_spearman_cosine | sts-dev-64_spearman_cosine | sts-dev-768_spearman_cosine | 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 |
+|:------:|:----:|:-------------:|:-------:|:---------------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
+| 0.5917 | 100  | 21.7032       | 21.7030 | 0.8030                      | 0.8124                      | 0.8205                      | 0.7839                     | 0.8215                      | -                            | -                            | -                            | -                           | -                            |
+| 1.1834 | 200  | 21.4019       | 24.0898 | 0.7839                      | 0.7972                      | 0.8038                      | 0.7680                     | 0.8062                      | -                            | -                            | -                            | -                           | -                            |
+| 1.7751 | 300  | 21.2168       | 22.5421 | 0.7909                      | 0.8027                      | 0.8058                      | 0.7786                     | 0.8068                      | -                            | -                            | -                            | -                           | -                            |
+| 2.3669 | 400  | 20.7049       | 23.6522 | 0.7938                      | 0.8049                      | 0.8108                      | 0.7873                     | 0.8123                      | -                            | -                            | -                            | -                           | -                            |
+| 2.9586 | 500  | 20.5077       | 23.6100 | 0.8017                      | 0.8116                      | 0.8155                      | 0.7893                     | 0.8185                      | -                            | -                            | -                            | -                           | -                            |
+| 3.5503 | 600  | 19.2725       | 24.7539 | 0.8133                      | 0.8254                      | 0.8291                      | 0.8032                     | 0.8314                      | -                            | -                            | -                            | -                           | -                            |
+| 4.1420 | 700  | 19.0841       | 26.5286 | 0.8210                      | 0.8298                      | 0.8333                      | 0.8102                     | 0.8333                      | -                            | -                            | -                            | -                           | -                            |
+| 4.7337 | 800  | 18.6847       | 26.8158 | 0.8198                      | 0.8304                      | 0.8333                      | 0.8077                     | 0.8343                      | -                            | -                            | -                            | -                           | -                            |
+| 5.0    | 845  | -             | -       | -                           | -                           | -                           | -                          | -                           | 0.8692                       | 0.8763                       | 0.8800                       | 0.8621                      | 0.8813                       |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- 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}
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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 +1,28 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.1",
+    "pytorch": "2.3.0+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 sha256:6a936de3306ace5e039eda3a274983deea2ab160c3532c04d599ec8a3a9b9e53
+size 2239607176

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": 512,
+  "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 sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}