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 +1,1209 @@
+---
+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 está acompañando a una mujer en el camino.
+  - Dos mujeres están cantando una hermosa canción.
+- source_sentence: La mujer está cortando papas.
+  sentences:
+  - Una mujer está cortando patatas.
+  - Los patos blancos se encuentran parados en el suelo.
+  - Hay una banda tocando en el escenario principal.
+- source_sentence: Un hombre está buscando algo.
+  sentences:
+  - En un mercado de granjeros, se encuentra un hombre.
+  - Romney filmó en una reunión privada de financiadores
+  - Dos perros de color negro están jugando en la hierba.
+- source_sentence: Un hombre saltando la cuerda.
+  sentences:
+  - Un hombre está saltando la cuerda.
+  - La capital de Siria fue golpeada por dos explosiones
+  - Los gatitos están comiendo de los platos.
+- source_sentence: El avión está tocando tierra.
+  sentences:
+  - El avión animado se encuentra en proceso de aterrizaje.
+  - Un pequeño niño montado en un columpio en el parque.
+  - Una persona de sexo femenino está cortando una cebolla.
+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: 0.8382359637067547
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8429605562993187
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8336600898033378
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8448900621318144
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8328580183902631
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8441561677427524
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8287262441829462
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8322746204974042
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8382359637067547
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8448900621318144
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8334610747047482
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8405630189692351
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8316848819512679
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8426142019940397
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8305903222472721
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8415256700272777
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8172993617433827
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.823043401157181
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8334610747047482
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8426142019940397
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8240056098321313
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8355774999921849
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8261458415991961
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8355100986320139
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.825647934422587
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8362336344962497
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7924886689283153
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7992788592975302
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8261458415991961
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8362336344962497
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8098656853945027
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8304511476467773
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8208946291392102
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8308359029901535
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8195023110971954
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8302481276550623
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7412744037070784
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7489986968697009
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8208946291392102
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8308359029901535
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.7777717898212414
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8152005256760807
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8007095698339157
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8116493253806699
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8000905317852872
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8110794468804238
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6540905690432955
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6589924104221199
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8007095698339157
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8152005256760807
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 32
+      type: sts-dev-32
+    metrics:
+    - type: pearson_cosine
+      value: 0.7276908730898617
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7805691037554072
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7659952363354546
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7751944660837697
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7674462214503804
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.7773298298599879
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5395044219284906
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5341543426421572
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7674462214503804
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.7805691037554072
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 16
+      type: sts-dev-16
+    metrics:
+    - type: pearson_cosine
+      value: 0.6737235484120327
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7425360948217027
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7187007732867645
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7279621825071231
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7234911258158329
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.7374355146279606
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.44701957007430754
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.44243975098384164
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7234911258158329
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.7425360948217027
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8637130740455785
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8774757245850818
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8739327947840198
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8771247494149252
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8742964420051067
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8774039769000851
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8587248460103846
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8692624735733635
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8742964420051067
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8774757245850818
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8608902316971913
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8761454408181157
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8723366100239835
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8755119028724399
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8727143818945785
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8758699632438892
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8498181878456328
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8568165420931783
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8727143818945785
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8761454408181157
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8546354043013908
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.871536658256446
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8697716394077537
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8737030599161743
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.86989853825415
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8736845554686979
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8131428680674924
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8076436370339797
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.86989853825415
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8737030599161743
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8387977115140051
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8645489592292456
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8611375341227384
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8667215229295422
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.862154474303328
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8680162798983022
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7492475609746636
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7363955675375832
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.862154474303328
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8680162798983022
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8168102869303625
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8585329796388539
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8518107264951738
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8606717941407515
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8533959511853835
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8623753165991692
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6646337116783656
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6473141838302237
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8533959511853835
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8623753165991692
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 32
+      type: sts-test-32
+    metrics:
+    - type: pearson_cosine
+      value: 0.7813945227753345
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8424823964509079
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8315336527432531
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8431756901550471
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8345328653107531
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8466076672836096
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5520860449837447
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5319238671245338
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8345328653107531
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8466076672836096
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 16
+      type: sts-test-16
+    metrics:
+    - type: pearson_cosine
+      value: 0.7198004009567176
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8072120165730962
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7805727606105963
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7997833060148871
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7879106231813758
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8090073332632988
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.44957276876149327
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.4411623904572447
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7879106231813758
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8090073332632988
+      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-768-16-5e")
+# Run inference
+sentences = [
+    'El avión está tocando tierra.',
+    'El avión animado se encuentra en proceso de aterrizaje.',
+    'Un pequeño niño montado en un columpio en el parque.',
+]
+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      | 0.8382    |
+| **spearman_cosine** | **0.843** |
+| pearson_manhattan   | 0.8337    |
+| spearman_manhattan  | 0.8449    |
+| pearson_euclidean   | 0.8329    |
+| spearman_euclidean  | 0.8442    |
+| pearson_dot         | 0.8287    |
+| spearman_dot        | 0.8323    |
+| pearson_max         | 0.8382    |
+| spearman_max        | 0.8449    |
+
+#### 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      | 0.8335     |
+| **spearman_cosine** | **0.8406** |
+| pearson_manhattan   | 0.8317     |
+| spearman_manhattan  | 0.8426     |
+| pearson_euclidean   | 0.8306     |
+| spearman_euclidean  | 0.8415     |
+| pearson_dot         | 0.8173     |
+| spearman_dot        | 0.823      |
+| pearson_max         | 0.8335     |
+| spearman_max        | 0.8426     |
+
+#### 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      | 0.824      |
+| **spearman_cosine** | **0.8356** |
+| pearson_manhattan   | 0.8261     |
+| spearman_manhattan  | 0.8355     |
+| pearson_euclidean   | 0.8256     |
+| spearman_euclidean  | 0.8362     |
+| pearson_dot         | 0.7925     |
+| spearman_dot        | 0.7993     |
+| pearson_max         | 0.8261     |
+| spearman_max        | 0.8362     |
+
+#### 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      | 0.8099     |
+| **spearman_cosine** | **0.8305** |
+| pearson_manhattan   | 0.8209     |
+| spearman_manhattan  | 0.8308     |
+| pearson_euclidean   | 0.8195     |
+| spearman_euclidean  | 0.8302     |
+| pearson_dot         | 0.7413     |
+| spearman_dot        | 0.749      |
+| pearson_max         | 0.8209     |
+| spearman_max        | 0.8308     |
+
+#### 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      | 0.7778     |
+| **spearman_cosine** | **0.8152** |
+| pearson_manhattan   | 0.8007     |
+| spearman_manhattan  | 0.8116     |
+| pearson_euclidean   | 0.8001     |
+| spearman_euclidean  | 0.8111     |
+| pearson_dot         | 0.6541     |
+| spearman_dot        | 0.659      |
+| pearson_max         | 0.8007     |
+| spearman_max        | 0.8152     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-32`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7277     |
+| **spearman_cosine** | **0.7806** |
+| pearson_manhattan   | 0.766      |
+| spearman_manhattan  | 0.7752     |
+| pearson_euclidean   | 0.7674     |
+| spearman_euclidean  | 0.7773     |
+| pearson_dot         | 0.5395     |
+| spearman_dot        | 0.5342     |
+| pearson_max         | 0.7674     |
+| spearman_max        | 0.7806     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-16`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6737     |
+| **spearman_cosine** | **0.7425** |
+| pearson_manhattan   | 0.7187     |
+| spearman_manhattan  | 0.728      |
+| pearson_euclidean   | 0.7235     |
+| spearman_euclidean  | 0.7374     |
+| pearson_dot         | 0.447      |
+| spearman_dot        | 0.4424     |
+| pearson_max         | 0.7235     |
+| spearman_max        | 0.7425     |
+
+#### 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      | 0.8637     |
+| **spearman_cosine** | **0.8775** |
+| pearson_manhattan   | 0.8739     |
+| spearman_manhattan  | 0.8771     |
+| pearson_euclidean   | 0.8743     |
+| spearman_euclidean  | 0.8774     |
+| pearson_dot         | 0.8587     |
+| spearman_dot        | 0.8693     |
+| pearson_max         | 0.8743     |
+| spearman_max        | 0.8775     |
+
+#### 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      | 0.8609     |
+| **spearman_cosine** | **0.8761** |
+| pearson_manhattan   | 0.8723     |
+| spearman_manhattan  | 0.8755     |
+| pearson_euclidean   | 0.8727     |
+| spearman_euclidean  | 0.8759     |
+| pearson_dot         | 0.8498     |
+| spearman_dot        | 0.8568     |
+| pearson_max         | 0.8727     |
+| spearman_max        | 0.8761     |
+
+#### 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      | 0.8546     |
+| **spearman_cosine** | **0.8715** |
+| pearson_manhattan   | 0.8698     |
+| spearman_manhattan  | 0.8737     |
+| pearson_euclidean   | 0.8699     |
+| spearman_euclidean  | 0.8737     |
+| pearson_dot         | 0.8131     |
+| spearman_dot        | 0.8076     |
+| pearson_max         | 0.8699     |
+| spearman_max        | 0.8737     |
+
+#### 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      | 0.8388     |
+| **spearman_cosine** | **0.8645** |
+| pearson_manhattan   | 0.8611     |
+| spearman_manhattan  | 0.8667     |
+| pearson_euclidean   | 0.8622     |
+| spearman_euclidean  | 0.868      |
+| pearson_dot         | 0.7492     |
+| spearman_dot        | 0.7364     |
+| pearson_max         | 0.8622     |
+| spearman_max        | 0.868      |
+
+#### 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      | 0.8168     |
+| **spearman_cosine** | **0.8585** |
+| pearson_manhattan   | 0.8518     |
+| spearman_manhattan  | 0.8607     |
+| pearson_euclidean   | 0.8534     |
+| spearman_euclidean  | 0.8624     |
+| pearson_dot         | 0.6646     |
+| spearman_dot        | 0.6473     |
+| pearson_max         | 0.8534     |
+| spearman_max        | 0.8624     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-32`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7814     |
+| **spearman_cosine** | **0.8425** |
+| pearson_manhattan   | 0.8315     |
+| spearman_manhattan  | 0.8432     |
+| pearson_euclidean   | 0.8345     |
+| spearman_euclidean  | 0.8466     |
+| pearson_dot         | 0.5521     |
+| spearman_dot        | 0.5319     |
+| pearson_max         | 0.8345     |
+| spearman_max        | 0.8466     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-16`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7198     |
+| **spearman_cosine** | **0.8072** |
+| pearson_manhattan   | 0.7806     |
+| spearman_manhattan  | 0.7998     |
+| pearson_euclidean   | 0.7879     |
+| spearman_euclidean  | 0.809      |
+| pearson_dot         | 0.4496     |
+| spearman_dot        | 0.4412     |
+| pearson_max         | 0.7879     |
+| spearman_max        | 0.809      |
+
+<!--
+## 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,
+          32,
+          16
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          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,
+          32,
+          16
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          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-16_spearman_cosine | sts-dev-256_spearman_cosine | sts-dev-32_spearman_cosine | sts-dev-512_spearman_cosine | sts-dev-64_spearman_cosine | sts-dev-768_spearman_cosine | sts-test-128_spearman_cosine | sts-test-16_spearman_cosine | sts-test-256_spearman_cosine | sts-test-32_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
+|:------:|:----:|:-------------:|:-------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
+| 0.5917 | 100  | 30.7503       | 30.6172 | 0.8117                      | 0.7110                     | 0.8179                      | 0.7457                     | 0.8244                      | 0.7884                     | 0.8252                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 1.1834 | 200  | 30.4696       | 32.6422 | 0.7952                      | 0.7198                     | 0.8076                      | 0.7491                     | 0.8125                      | 0.7813                     | 0.8142                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 1.7751 | 300  | 29.9233       | 31.5469 | 0.8152                      | 0.7435                     | 0.8250                      | 0.7737                     | 0.8302                      | 0.8006                     | 0.8305                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 2.3669 | 400  | 29.0716       | 31.8088 | 0.8183                      | 0.7405                     | 0.8248                      | 0.7758                     | 0.8299                      | 0.8057                     | 0.8324                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 2.9586 | 500  | 28.7971       | 32.6032 | 0.8176                      | 0.7430                     | 0.8241                      | 0.7777                     | 0.8289                      | 0.8025                     | 0.8316                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 3.5503 | 600  | 27.4766       | 34.7911 | 0.8241                      | 0.7400                     | 0.8314                      | 0.7730                     | 0.8369                      | 0.8061                     | 0.8394                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 4.1420 | 700  | 27.0639       | 35.7418 | 0.8294                      | 0.7466                     | 0.8354                      | 0.7784                     | 0.8389                      | 0.8107                     | 0.8409                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 4.7337 | 800  | 26.5119       | 36.2014 | 0.8305                      | 0.7425                     | 0.8356                      | 0.7806                     | 0.8406                      | 0.8152                     | 0.8430                      | -                            | -                           | -                            | -                           | -                            | -                           | -                            |
+| 5.0    | 845  | -             | -       | -                           | -                          | -                           | -                          | -                           | -                          | -                           | 0.8645                       | 0.8072                      | 0.8715                       | 0.8425                      | 0.8761                       | 0.8585                      | 0.8775                       |
+
+
+### 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:b31e31b46df73827fafdccebb896150b658d9e668ba5cee3147a5767ab860e72
+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>"
+}