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 +1,890 @@
+---
+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:6468
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: El seu objecte és que -prèviament a la seva execució material-
+    l'Ajuntament comprovi l'adequació de l’actuació a la normativa i planejament,
+    així com a les ordenances municipals sobre l’ús del sòl i edificació.
+  sentences:
+  - Quin és el paper de les ordenances municipals en la llicència d'extracció d'àrids
+    i explotació de pedreres?
+  - Quin és el percentatge de bonificació que es pot obtenir?
+  - Quin és el propòsit del tràmit d'adjudicació d'habitatges socials i d'emergència?
+- source_sentence: La renda és un element important en la tramitació d'un ajornament
+    o fraccionament, ja que es té en compte per determinar si el sol·licitant compleix
+    els requisits per a sol·licitar el criteri excepcional.
+  sentences:
+  - Quin és el paper de la renda en la tramitació d'un ajornament o fraccionament?
+  - Quin és l'objectiu del tràmit C03?
+  - Quin és el paper de les ordenances municipals en la llicència de parcel·lació?
+- source_sentence: L’article 14 de la llei 39/2015 estableix l’obligatorietat de l’ús
+    de mitjans electrònics, informàtics o telemàtics per desenvolupar totes les fases
+    del procediment de contractació.
+  sentences:
+  - Quin és el paper de les ordenances municipals sobre l’ús del sòl i edificació
+    en el tràmit de modificació substancial de la llicència d'obres?
+  - Quin és el requisit per a la intervenció d'una persona tècnica?
+  - Quin és el propòsit de l’article 14 de la llei 39/2015?
+- source_sentence: El seu objecte és que -prèviament a la seva execució material-
+    l'Ajuntament comprovi l'adequació de l’actuació a la normativa i planejament,
+    així com a les ordenances municipals sobre l’ús del sòl i edificació.
+  sentences:
+  - Quin és el paper del planejament en el tràmit de llicència d'obres per l'obertura,
+    la pavimentació i la modificació de camins rurals?
+  - Quin és el requisit per presentar una sol·licitud?
+  - Quin és el resultat de la falta de presentació de la documentació tècnica corresponent?
+- source_sentence: L’Ajuntament de Sant Quirze del Vallès reconeix un dret preferent
+    al titular del dret funerari sobre la corresponent sepultura o al successor o
+    causahavent de l’anterior titular d’aquest dret, que permet adquirir de nou el
+    dret funerari referit, sobre la mateixa sepultura, un cop el dret atorgat ha exhaurit
+    el termini de vigència
+  sentences:
+  - Quin és el requisit per a les instal·lacions solars per mantenir la bonificació?
+  - Quin és el paper del cens electoral en les eleccions?
+  - Quan es pot adquirir de nou el dret funerari?
+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: 0.10173160173160173
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.27705627705627706
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.36796536796536794
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.48268398268398266
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.10173160173160173
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09235209235209235
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0735930735930736
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04826839826839826
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.10173160173160173
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.27705627705627706
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.36796536796536794
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.48268398268398266
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.27573421573267004
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21126485947914525
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.22874042563037256
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.11904761904761904
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.29004329004329005
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3658008658008658
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.49567099567099565
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.11904761904761904
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09668109668109669
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07316017316017315
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.049567099567099565
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.11904761904761904
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.29004329004329005
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3658008658008658
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.49567099567099565
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2892077987787756
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.22525767882910738
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.24276232307204765
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.10822510822510822
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2662337662337662
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.36363636363636365
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5064935064935064
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.10822510822510822
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08874458874458875
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07272727272727272
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.050649350649350645
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.10822510822510822
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2662337662337662
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.36363636363636365
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5064935064935064
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.28386807922368074
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21557239057239053
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.23234161860560523
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.11471861471861472
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.24025974025974026
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3398268398268398
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4805194805194805
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.11471861471861472
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08008658008658008
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06796536796536796
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04805194805194805
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.11471861471861472
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.24025974025974026
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3398268398268398
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4805194805194805
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2749619650624931
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21201642273070856
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.23043548788604293
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.11255411255411256
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.26406926406926406
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.329004329004329
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.487012987012987
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.11255411255411256
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08802308802308802
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0658008658008658
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.048701298701298704
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.11255411255411256
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.26406926406926406
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.329004329004329
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.487012987012987
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.27907708560411776
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21522795987081703
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.23398722217128723
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1038961038961039
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2619047619047619
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3354978354978355
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.474025974025974
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1038961038961039
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0873015873015873
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0670995670995671
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0474025974025974
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1038961038961039
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2619047619047619
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3354978354978355
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.474025974025974
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2700415740619265
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.20714285714285718
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.22556246902969454
+      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-SQV-007-5ep")
+# Run inference
+sentences = [
+    'L’Ajuntament de Sant Quirze del Vallès reconeix un dret preferent al titular del dret funerari sobre la corresponent sepultura o al successor o causahavent de l’anterior titular d’aquest dret, que permet adquirir de nou el dret funerari referit, sobre la mateixa sepultura, un cop el dret atorgat ha exhaurit el termini de vigència',
+    'Quan es pot adquirir de nou el dret funerari?',
+    'Quin és el paper del cens electoral en les eleccions?',
+]
+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   | 0.1017     |
+| cosine_accuracy@3   | 0.2771     |
+| cosine_accuracy@5   | 0.368      |
+| cosine_accuracy@10  | 0.4827     |
+| cosine_precision@1  | 0.1017     |
+| cosine_precision@3  | 0.0924     |
+| cosine_precision@5  | 0.0736     |
+| cosine_precision@10 | 0.0483     |
+| cosine_recall@1     | 0.1017     |
+| cosine_recall@3     | 0.2771     |
+| cosine_recall@5     | 0.368      |
+| cosine_recall@10    | 0.4827     |
+| cosine_ndcg@10      | 0.2757     |
+| cosine_mrr@10       | 0.2113     |
+| **cosine_map@100**  | **0.2287** |
+
+#### 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   | 0.119      |
+| cosine_accuracy@3   | 0.29       |
+| cosine_accuracy@5   | 0.3658     |
+| cosine_accuracy@10  | 0.4957     |
+| cosine_precision@1  | 0.119      |
+| cosine_precision@3  | 0.0967     |
+| cosine_precision@5  | 0.0732     |
+| cosine_precision@10 | 0.0496     |
+| cosine_recall@1     | 0.119      |
+| cosine_recall@3     | 0.29       |
+| cosine_recall@5     | 0.3658     |
+| cosine_recall@10    | 0.4957     |
+| cosine_ndcg@10      | 0.2892     |
+| cosine_mrr@10       | 0.2253     |
+| **cosine_map@100**  | **0.2428** |
+
+#### 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   | 0.1082     |
+| cosine_accuracy@3   | 0.2662     |
+| cosine_accuracy@5   | 0.3636     |
+| cosine_accuracy@10  | 0.5065     |
+| cosine_precision@1  | 0.1082     |
+| cosine_precision@3  | 0.0887     |
+| cosine_precision@5  | 0.0727     |
+| cosine_precision@10 | 0.0506     |
+| cosine_recall@1     | 0.1082     |
+| cosine_recall@3     | 0.2662     |
+| cosine_recall@5     | 0.3636     |
+| cosine_recall@10    | 0.5065     |
+| cosine_ndcg@10      | 0.2839     |
+| cosine_mrr@10       | 0.2156     |
+| **cosine_map@100**  | **0.2323** |
+
+#### 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   | 0.1147     |
+| cosine_accuracy@3   | 0.2403     |
+| cosine_accuracy@5   | 0.3398     |
+| cosine_accuracy@10  | 0.4805     |
+| cosine_precision@1  | 0.1147     |
+| cosine_precision@3  | 0.0801     |
+| cosine_precision@5  | 0.068      |
+| cosine_precision@10 | 0.0481     |
+| cosine_recall@1     | 0.1147     |
+| cosine_recall@3     | 0.2403     |
+| cosine_recall@5     | 0.3398     |
+| cosine_recall@10    | 0.4805     |
+| cosine_ndcg@10      | 0.275      |
+| cosine_mrr@10       | 0.212      |
+| **cosine_map@100**  | **0.2304** |
+
+#### 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   | 0.1126    |
+| cosine_accuracy@3   | 0.2641    |
+| cosine_accuracy@5   | 0.329     |
+| cosine_accuracy@10  | 0.487     |
+| cosine_precision@1  | 0.1126    |
+| cosine_precision@3  | 0.088     |
+| cosine_precision@5  | 0.0658    |
+| cosine_precision@10 | 0.0487    |
+| cosine_recall@1     | 0.1126    |
+| cosine_recall@3     | 0.2641    |
+| cosine_recall@5     | 0.329     |
+| cosine_recall@10    | 0.487     |
+| cosine_ndcg@10      | 0.2791    |
+| cosine_mrr@10       | 0.2152    |
+| **cosine_map@100**  | **0.234** |
+
+#### 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   | 0.1039     |
+| cosine_accuracy@3   | 0.2619     |
+| cosine_accuracy@5   | 0.3355     |
+| cosine_accuracy@10  | 0.474      |
+| cosine_precision@1  | 0.1039     |
+| cosine_precision@3  | 0.0873     |
+| cosine_precision@5  | 0.0671     |
+| cosine_precision@10 | 0.0474     |
+| cosine_recall@1     | 0.1039     |
+| cosine_recall@3     | 0.2619     |
+| cosine_recall@5     | 0.3355     |
+| cosine_recall@10    | 0.474      |
+| cosine_ndcg@10      | 0.27       |
+| cosine_mrr@10       | 0.2071     |
+| **cosine_map@100**  | **0.2256** |
+
+<!--
+## 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: 6,468 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: 5 tokens</li><li>mean: 39.4 tokens</li><li>max: 168 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.48 tokens</li><li>max: 44 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                           | anchor                                                                                                                               |
+  |:-------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Aquest tràmit permet la inscripció al padró dels canvis de domicili dins de Sant Quirze del Vallès...</code> | <code>Quin és el benefici de la inscripció al Padró d'Habitants?</code>                                                              |
+  | <code>Els recursos que es poden oferir al banc de recursos són: MATERIALS, PROFESSIONALS i SOCIALS.</code>         | <code>Quins tipus de recursos es poden oferir al banc de recursos?</code>                                                            |
+  | <code>El termini per a la presentació de sol·licituds serà del 8 al 21 de maig de 2024, ambdós inclosos.</code>    | <code>Quin és el termini per a la presentació de sol·licituds per a la preinscripció a l'Escola Bressol Municipal El Patufet?</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 |
+|:---------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.3951    | 10     | 4.4042        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.7901    | 20     | 2.9471        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.9877    | 25     | -             | 0.2293                  | 0.2045                 | 0.2099                 | 0.2138                 | 0.1717                | 0.2242                 |
+| 1.1852    | 30     | 2.2351        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.5802    | 40     | 1.5289        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.9753    | 50     | 1.2045        | 0.2332                  | 0.2182                 | 0.2277                 | 0.2221                 | 0.2051                | 0.2248                 |
+| 2.3704    | 60     | 0.9435        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.7654    | 70     | 0.7958        | -                       | -                      | -                      | -                      | -                     | -                      |
+| **2.963** | **75** | **-**         | **0.2379**              | **0.2352**             | **0.2276**             | **0.2204**             | **0.2138**            | **0.2235**             |
+| 3.1605    | 80     | 0.6703        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.5556    | 90     | 0.6162        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9506    | 100    | 0.6079        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9901    | 101    | -             | 0.2251                  | 0.2307                 | 0.2201                 | 0.2343                 | 0.2210                | 0.2348                 |
+| 4.3457    | 110    | 0.5085        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.7407    | 120    | 0.5248        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.9383    | 125    | -             | 0.2287                  | 0.2340                 | 0.2304                 | 0.2323                 | 0.2256                | 0.2428                 |
+
+* 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 sha256:35470e56af8e792a6a49f4e5c68ac7c672d25d39558dfcb6a5a63003ffa09f6b
+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>"
+}