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 +1,887 @@
+---
+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:6749
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: La presentació de la comunicació prèvia, acompanyada de la documentació
+    exigida, habilita a la persona interessada a executar els actes que s'hi descriuen,
+    des del dia de la seva presentació, sens perjudici de les facultats de comprovació,
+    control i inspecció de l'Ajuntament.
+  sentences:
+  - Quin és el resultat de la llicència d'usos i obres provisionals en relació amb
+    altres autoritzacions administratives?
+  - Quin és el paper de la persona interessada en aquest tràmit?
+  - Quin és el tipus d'impost que es beneficia d'aquest tràmit?
+- source_sentence: L'aportació de residus a la Deixalleria municipal us permet obtenir
+    una bonificació de la taxa de residus del 15%.
+  sentences:
+  - Quin és el benefici de la Deixalleria municipal?
+  - Quin és el benefici de tenir un volant de convivència?
+  - Quin és el benefici de tenir el certificat del nombre d’habitants i habitatges
+    del Padró d’Habitants?
+- source_sentence: La presentació de la comunicació prèvia, acompanyada de la documentació
+    exigida, habilita a la persona interessada a executar els actes que s'hi descriuen,
+    des del dia de la seva presentació, sens perjudici de les facultats de comprovació,
+    control i inspecció de l’Ajuntament.
+  sentences:
+  - Quin és el resultat de la presentació de la documentació exigida?
+  - Quina és la condició per a la concessió de la bonificació?
+  - On es troben els drets funeraris que es volen canviar?
+- source_sentence: Renovació de concessió de drets funeraris a llarg termini (cementiri)
+  sentences:
+  - Quin és el requisit per aturar o estacionar el vehicle amb la targeta d'aparcament
+    de transport col·lectiu?
+  - Quin és el benefici de la concessió de drets funeraris a llarg termini?
+  - Quin és el tipus de residus que es requereixen per a la bonificació?
+- source_sentence: La presentació de la sol·licitud no dona dret al muntatge de la
+    parada.
+  sentences:
+  - Quin és el motiu per canviar la persona titular dels drets funeraris?
+  - Quin és el propòsit de la reunió informativa i de coordinació?
+  - Quin és el requisit per a la presentació de la sol·licitud d’autorització?
+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: 0.044
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.116
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3506666666666667
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.044
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03866666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.036
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03506666666666667
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.044
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.116
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3506666666666667
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16592235166459846
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11099682539682543
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13414156200645738
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.04133333333333333
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.116
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17866666666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3626666666666667
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.04133333333333333
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03866666666666666
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03573333333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03626666666666667
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04133333333333333
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.116
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17866666666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3626666666666667
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16902152680215465
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11157989417989429
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13412743689937764
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.04666666666666667
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.116
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17866666666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.356
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.04666666666666667
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03866666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03573333333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03560000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04666666666666667
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.116
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17866666666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.356
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16772455344289713
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11209576719576728
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13459804045251053
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.03866666666666667
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.10666666666666667
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17066666666666666
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3413333333333333
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.03866666666666667
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.035555555555555556
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.034133333333333335
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.034133333333333335
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.03866666666666667
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.10666666666666667
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17066666666666666
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3413333333333333
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15868936356762114
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10455608465608475
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12901246498692368
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.04933333333333333
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.12266666666666666
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.19866666666666666
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.36666666666666664
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.04933333333333333
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.040888888888888884
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.039733333333333336
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03666666666666667
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04933333333333333
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.12266666666666666
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.19866666666666666
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.36666666666666664
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.17594327999948436
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11901798941798955
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14198426639116846
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.037333333333333336
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.09466666666666666
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.15733333333333333
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.34
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.037333333333333336
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03155555555555555
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03146666666666667
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.034
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.037333333333333336
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.09466666666666666
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.15733333333333333
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.34
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.1535334048621682
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.09865185185185205
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12262604132052936
+      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/sqv2")
+# Run inference
+sentences = [
+    'La presentació de la sol·licitud no dona dret al muntatge de la parada.',
+    'Quin és el requisit per a la presentació de la sol·licitud d’autorització?',
+    'Quin és el motiu per canviar la persona titular dels drets funeraris?',
+]
+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   | 0.044      |
+| cosine_accuracy@3   | 0.116      |
+| cosine_accuracy@5   | 0.18       |
+| cosine_accuracy@10  | 0.3507     |
+| cosine_precision@1  | 0.044      |
+| cosine_precision@3  | 0.0387     |
+| cosine_precision@5  | 0.036      |
+| cosine_precision@10 | 0.0351     |
+| cosine_recall@1     | 0.044      |
+| cosine_recall@3     | 0.116      |
+| cosine_recall@5     | 0.18       |
+| cosine_recall@10    | 0.3507     |
+| cosine_ndcg@10      | 0.1659     |
+| cosine_mrr@10       | 0.111      |
+| **cosine_map@100**  | **0.1341** |
+
+#### 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   | 0.0413     |
+| cosine_accuracy@3   | 0.116      |
+| cosine_accuracy@5   | 0.1787     |
+| cosine_accuracy@10  | 0.3627     |
+| cosine_precision@1  | 0.0413     |
+| cosine_precision@3  | 0.0387     |
+| cosine_precision@5  | 0.0357     |
+| cosine_precision@10 | 0.0363     |
+| cosine_recall@1     | 0.0413     |
+| cosine_recall@3     | 0.116      |
+| cosine_recall@5     | 0.1787     |
+| cosine_recall@10    | 0.3627     |
+| cosine_ndcg@10      | 0.169      |
+| cosine_mrr@10       | 0.1116     |
+| **cosine_map@100**  | **0.1341** |
+
+#### 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   | 0.0467     |
+| cosine_accuracy@3   | 0.116      |
+| cosine_accuracy@5   | 0.1787     |
+| cosine_accuracy@10  | 0.356      |
+| cosine_precision@1  | 0.0467     |
+| cosine_precision@3  | 0.0387     |
+| cosine_precision@5  | 0.0357     |
+| cosine_precision@10 | 0.0356     |
+| cosine_recall@1     | 0.0467     |
+| cosine_recall@3     | 0.116      |
+| cosine_recall@5     | 0.1787     |
+| cosine_recall@10    | 0.356      |
+| cosine_ndcg@10      | 0.1677     |
+| cosine_mrr@10       | 0.1121     |
+| **cosine_map@100**  | **0.1346** |
+
+#### 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   | 0.0387    |
+| cosine_accuracy@3   | 0.1067    |
+| cosine_accuracy@5   | 0.1707    |
+| cosine_accuracy@10  | 0.3413    |
+| cosine_precision@1  | 0.0387    |
+| cosine_precision@3  | 0.0356    |
+| cosine_precision@5  | 0.0341    |
+| cosine_precision@10 | 0.0341    |
+| cosine_recall@1     | 0.0387    |
+| cosine_recall@3     | 0.1067    |
+| cosine_recall@5     | 0.1707    |
+| cosine_recall@10    | 0.3413    |
+| cosine_ndcg@10      | 0.1587    |
+| cosine_mrr@10       | 0.1046    |
+| **cosine_map@100**  | **0.129** |
+
+#### 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   | 0.0493    |
+| cosine_accuracy@3   | 0.1227    |
+| cosine_accuracy@5   | 0.1987    |
+| cosine_accuracy@10  | 0.3667    |
+| cosine_precision@1  | 0.0493    |
+| cosine_precision@3  | 0.0409    |
+| cosine_precision@5  | 0.0397    |
+| cosine_precision@10 | 0.0367    |
+| cosine_recall@1     | 0.0493    |
+| cosine_recall@3     | 0.1227    |
+| cosine_recall@5     | 0.1987    |
+| cosine_recall@10    | 0.3667    |
+| cosine_ndcg@10      | 0.1759    |
+| cosine_mrr@10       | 0.119     |
+| **cosine_map@100**  | **0.142** |
+
+#### 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   | 0.0373     |
+| cosine_accuracy@3   | 0.0947     |
+| cosine_accuracy@5   | 0.1573     |
+| cosine_accuracy@10  | 0.34       |
+| cosine_precision@1  | 0.0373     |
+| cosine_precision@3  | 0.0316     |
+| cosine_precision@5  | 0.0315     |
+| cosine_precision@10 | 0.034      |
+| cosine_recall@1     | 0.0373     |
+| cosine_recall@3     | 0.0947     |
+| cosine_recall@5     | 0.1573     |
+| cosine_recall@10    | 0.34       |
+| cosine_ndcg@10      | 0.1535     |
+| cosine_mrr@10       | 0.0987     |
+| **cosine_map@100**  | **0.1226** |
+
+<!--
+## 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: 6,749 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: 6 tokens</li><li>mean: 42.03 tokens</li><li>max: 106 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.32 tokens</li><li>max: 54 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                            | anchor                                                                                       |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------|
+  | <code>Aquest tràmit us permet compensar deutes de naturalesa pública a favor de l'Ajuntament, sigui quin sigui el seu estat (voluntari/executiu), amb crèdits reconeguts per aquest a favor del mateix deutor, i que el seu estat sigui pendent de pagament.</code> | <code>Quin és el benefici de la compensació de deutes amb crèdits?</code>                    |
+  | <code>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.</code>                                     | <code>Quin és el paper de les ordenances municipals en aquest tràmit?</code>                 |
+  | <code>Comunicació prèvia del manteniment en espais, zones o instal·lacions comunitàries interiors dels edificis (reparació i/o millora de materials).</code>                                                                                                        | <code>Quin és el límit del manteniment en espais comunitaris interiors dels edificis?</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 |
+|:----------:|:-------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.3791     | 10      | 3.0867        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.7583     | 20      | 2.4414        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.9858     | 26      | -             | 0.1266                  | 0.1255                 | 0.1232                 | 0.1257                 | 0.1091                | 0.1345                 |
+| 1.1351     | 30      | 1.7091        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.5142     | 40      | 1.2495        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.8934     | 50      | 0.9813        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.9692     | 52      | -             | 0.1315                  | 0.1325                 | 0.1285                 | 0.1328                 | 0.1218                | 0.1309                 |
+| 2.2701     | 60      | 0.6918        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.6493     | 70      | 0.7146        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.9905     | 79      | -             | 0.1370                  | 0.1344                 | 0.1355                 | 0.1338                 | 0.1269                | 0.1363                 |
+| 3.0261     | 80      | 0.6002        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.4052     | 90      | 0.4816        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.7844     | 100     | 0.4949        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9739     | 105     | -             | 0.1357                  | 0.1393                 | 0.1302                 | 0.1347                 | 0.1204                | 0.1354                 |
+| 4.1611     | 110     | 0.474         | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.5403     | 120     | 0.4692        | -                       | -                      | -                      | -                      | -                     | -                      |
+| **4.9194** | **130** | **0.4484**    | **0.1341**              | **0.142**              | **0.129**              | **0.1346**             | **0.1226**            | **0.1341**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.0
+- Transformers: 4.44.2
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.35.0.dev0
+- Datasets: 3.0.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### 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": "3.1.0",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.0+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 sha256:7340b94692f84db7711b9e23ffaec2518d22401832e2f1b8d6eb4fc781a7b2a4
+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>"
+}