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": true,
+  "pooling_mode_mean_tokens": false,
+  "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 +1,888 @@
+---
+base_model: BAAI/bge-m3
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:5214
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Pel que fa als avals, la Junta de Govern Local en sessió celebrada
+    el 4 de juliol de 2006, va aprovar els models d'aval en funció del concepte a
+    garantir.
+  sentences:
+  - Quin és el benefici de la unitat de queixes i suggeriments per a la qualitat dels
+    serveis de l'Ajuntament de Sitges?
+  - Quin és el paper de la Junta de Govern Local?
+  - Quin és el propòsit més important del tràmit de canvi de titular de la llicència
+    de gual?
+- source_sentence: Per a tenir dret a ésser inscrit en el Registre de Sol·licitants
+    d'Habitatge amb Protecció Oficial s'han de complir els procediments i els requisits
+    establerts per normativa.
+  sentences:
+  - Quin és el paper de la persona sol·licitant en la gestió de les fiances o dipòsits
+    d'una llicència d'obra?
+  - Quin és el benefici de complir els procediments i els requisits establerts per
+    normativa?
+  - Quin és el centre cultural que es troba a l'Escorxador de Sitges i ofereix activitats
+    culturals?
+- source_sentence: Aquest tràmit permet comunicar a l'Ajuntament de Sitges la finalització
+    de les obres de nova construcció, o bé aquelles que hagin estat objecte de modificació
+    substancial o d’ampliació quan per a l’autorització de les obres s’hagi exigit
+    un projecte tècnic i a l’empara d’una llicència urbanística d’obra major.
+  sentences:
+  - Què passa si la modificació no té efectes sobre les persones o el medi ambient?
+  - Quin és el requisit principal per a la gestió diària d'una colònia felina?
+  - Quin és el paper del tràmit de comunicació prèvia de primera utilització i ocupació
+    d'edificis i instal·lacions en el procés d'obtenció de la llicència urbanística
+    d’obra major?
+- source_sentence: Es tracta dels ajuts per a la realització de la Inspecció Tècnica
+    de l’Edifici (ITE) conjuntament amb l’elaboració dels certificats energètics.
+  sentences:
+  - Quins són els tipus de garanties que es poden ingressar?
+  - Quin és el procés d’elaboració dels certificats energètics?
+  - Quin és el paper de la consulta prèvia de classificació d'activitat en la tramitació
+    administrativa municipal?
+- source_sentence: Les queixes, observacions i suggeriments són una eina important
+    per a millorar la qualitat dels serveis municipals.
+  sentences:
+  - Quin és el propòsit dels ajuts econòmics?
+  - Què és el que es busca amb les queixes, observacions i suggeriments?
+  - Qui són les persones beneficiàries de l'ajut per a la creació de noves empreses?
+model-index:
+- name: SentenceTransformer based on BAAI/bge-m3
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14367088607594936
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2818565400843882
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3930379746835443
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5664556962025317
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14367088607594936
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09395218002812938
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07860759493670887
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05664556962025316
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14367088607594936
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2818565400843882
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3930379746835443
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5664556962025317
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.32426778614918705
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.25066212912731944
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2694799737895368
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1470464135021097
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2871308016877637
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.390084388185654
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5630801687763713
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1470464135021097
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09571026722925456
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07801687763713079
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.056308016877637125
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1470464135021097
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2871308016877637
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.390084388185654
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5630801687763713
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.32549268557195893
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.25325421940928294
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.272264774489146
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14177215189873418
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.28375527426160335
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3890295358649789
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5620253164556962
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14177215189873418
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09458509142053445
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07780590717299578
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05620253164556962
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14177215189873418
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.28375527426160335
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3890295358649789
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5620253164556962
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.322564230377663
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.24968421405130298
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.26885741426647297
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14345991561181434
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2831223628691983
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3850210970464135
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5550632911392405
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14345991561181434
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09437412095639944
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0770042194092827
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05550632911392406
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14345991561181434
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2831223628691983
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3850210970464135
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5550632911392405
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.3205268083804564
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.24917821981113142
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2685327848764784
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.13924050632911392
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2795358649789029
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3837552742616034
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5533755274261604
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.13924050632911392
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09317862165963431
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07675105485232067
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05533755274261602
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.13924050632911392
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2795358649789029
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3837552742616034
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5533755274261604
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.31759054947613424
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2457681166700155
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2649300065982546
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14029535864978904
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.27531645569620256
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.369831223628692
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5360759493670886
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14029535864978904
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09177215189873417
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0739662447257384
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.053607594936708865
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14029535864978904
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.27531645569620256
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.369831223628692
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5360759493670886
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.3099216271465372
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.24117783470631593
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2601649646918979
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-m3
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the json 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:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+<!-- - **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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("adriansanz/ST-tramits-sitges-005-5ep")
+# Run inference
+sentences = [
+    'Les queixes, observacions i suggeriments són una eina important per a millorar la qualitat dels serveis municipals.',
+    'Què és el que es busca amb les queixes, observacions i suggeriments?',
+    'Quin és el propòsit dels ajuts econòmics?',
+]
+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
+
+#### Information Retrieval
+* Dataset: `dim_1024`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1437     |
+| cosine_accuracy@3   | 0.2819     |
+| cosine_accuracy@5   | 0.393      |
+| cosine_accuracy@10  | 0.5665     |
+| cosine_precision@1  | 0.1437     |
+| cosine_precision@3  | 0.094      |
+| cosine_precision@5  | 0.0786     |
+| cosine_precision@10 | 0.0566     |
+| cosine_recall@1     | 0.1437     |
+| cosine_recall@3     | 0.2819     |
+| cosine_recall@5     | 0.393      |
+| cosine_recall@10    | 0.5665     |
+| cosine_ndcg@10      | 0.3243     |
+| cosine_mrr@10       | 0.2507     |
+| **cosine_map@100**  | **0.2695** |
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.147      |
+| cosine_accuracy@3   | 0.2871     |
+| cosine_accuracy@5   | 0.3901     |
+| cosine_accuracy@10  | 0.5631     |
+| cosine_precision@1  | 0.147      |
+| cosine_precision@3  | 0.0957     |
+| cosine_precision@5  | 0.078      |
+| cosine_precision@10 | 0.0563     |
+| cosine_recall@1     | 0.147      |
+| cosine_recall@3     | 0.2871     |
+| cosine_recall@5     | 0.3901     |
+| cosine_recall@10    | 0.5631     |
+| cosine_ndcg@10      | 0.3255     |
+| cosine_mrr@10       | 0.2533     |
+| **cosine_map@100**  | **0.2723** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1418     |
+| cosine_accuracy@3   | 0.2838     |
+| cosine_accuracy@5   | 0.389      |
+| cosine_accuracy@10  | 0.562      |
+| cosine_precision@1  | 0.1418     |
+| cosine_precision@3  | 0.0946     |
+| cosine_precision@5  | 0.0778     |
+| cosine_precision@10 | 0.0562     |
+| cosine_recall@1     | 0.1418     |
+| cosine_recall@3     | 0.2838     |
+| cosine_recall@5     | 0.389      |
+| cosine_recall@10    | 0.562      |
+| cosine_ndcg@10      | 0.3226     |
+| cosine_mrr@10       | 0.2497     |
+| **cosine_map@100**  | **0.2689** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1435     |
+| cosine_accuracy@3   | 0.2831     |
+| cosine_accuracy@5   | 0.385      |
+| cosine_accuracy@10  | 0.5551     |
+| cosine_precision@1  | 0.1435     |
+| cosine_precision@3  | 0.0944     |
+| cosine_precision@5  | 0.077      |
+| cosine_precision@10 | 0.0555     |
+| cosine_recall@1     | 0.1435     |
+| cosine_recall@3     | 0.2831     |
+| cosine_recall@5     | 0.385      |
+| cosine_recall@10    | 0.5551     |
+| cosine_ndcg@10      | 0.3205     |
+| cosine_mrr@10       | 0.2492     |
+| **cosine_map@100**  | **0.2685** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1392     |
+| cosine_accuracy@3   | 0.2795     |
+| cosine_accuracy@5   | 0.3838     |
+| cosine_accuracy@10  | 0.5534     |
+| cosine_precision@1  | 0.1392     |
+| cosine_precision@3  | 0.0932     |
+| cosine_precision@5  | 0.0768     |
+| cosine_precision@10 | 0.0553     |
+| cosine_recall@1     | 0.1392     |
+| cosine_recall@3     | 0.2795     |
+| cosine_recall@5     | 0.3838     |
+| cosine_recall@10    | 0.5534     |
+| cosine_ndcg@10      | 0.3176     |
+| cosine_mrr@10       | 0.2458     |
+| **cosine_map@100**  | **0.2649** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1403     |
+| cosine_accuracy@3   | 0.2753     |
+| cosine_accuracy@5   | 0.3698     |
+| cosine_accuracy@10  | 0.5361     |
+| cosine_precision@1  | 0.1403     |
+| cosine_precision@3  | 0.0918     |
+| cosine_precision@5  | 0.074      |
+| cosine_precision@10 | 0.0536     |
+| cosine_recall@1     | 0.1403     |
+| cosine_recall@3     | 0.2753     |
+| cosine_recall@5     | 0.3698     |
+| cosine_recall@10    | 0.5361     |
+| cosine_ndcg@10      | 0.3099     |
+| cosine_mrr@10       | 0.2412     |
+| **cosine_map@100**  | **0.2602** |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 5,214 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                           | anchor                                                                             |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 49.66 tokens</li><li>max: 149 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.85 tokens</li><li>max: 48 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                            | anchor                                                                              |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | <code>Ajuts per la reactivació de petites empreses i persones autònomes donades d’alta al règim especial de treballadors autònoms (RETA) amb una antiguitat superior als cinc anys (COVID19)</code> | <code>Quin és el requisit per a les petites empreses per rebre ajuts?</code>        |
+  | <code>En cas de no poder desenvolupar el projecte o activitat per la qual s'ha sol·licitat la subvenció, l'entitat beneficiària pot renunciar a la subvenció.</code>                                | <code>Puc renunciar a una subvenció si ja l'he rebut?</code>                        |
+  | <code>L’Espai Jove de Sitges és l'equipament municipal on els joves poden dur a terme iniciatives pròpies i on també es desenvolupen d’altres impulsades per la regidoria de Joventut.</code>       | <code>Quin és el paper de la regidoria de Joventut a l'Espai Jove de Sitges?</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.2
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `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`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-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`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.2
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_1024_cosine_map@100 | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.4908     | 10     | 3.3699        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.9816     | 20     | 1.8761        | 0.2565                  | 0.2430                 | 0.2509                 | 0.2499                 | 0.2301                | 0.2567                 |
+| 1.4724     | 30     | 1.3111        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.9632     | 40     | 0.8122        | 0.2636                  | 0.2578                 | 0.2629                 | 0.2639                 | 0.2486                | 0.2654                 |
+| 2.4540     | 50     | 0.5903        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.9448     | 60     | 0.4306        | -                       | -                      | -                      | -                      | -                     | -                      |
+| **2.9939** | **61** | **-**         | **0.2661**              | **0.2636**             | **0.2648**             | **0.2659**             | **0.2544**            | **0.2694**             |
+| 3.4356     | 70     | 0.3553        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9264     | 80     | 0.2925        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9755     | 81     | -             | 0.2701                  | 0.2621                 | 0.2663                 | 0.2706                 | 0.2602                | 0.2709                 |
+| 4.4172     | 90     | 0.2797        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.9080     | 100    | 0.267         | 0.2695                  | 0.2649                 | 0.2685                 | 0.2689                 | 0.2602                | 0.2723                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 0.35.0.dev0
+- Datasets: 3.0.1
+- 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}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "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": 8194,
+  "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": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1+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 sha256:94d1e7e7eaf7024d3a9c9a1530d38516661be1efb80dc6c6ed159fc5e57c1625
+size 2271064456

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": 8192,
+  "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:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}