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 +1,923 @@
+---
+base_model: BAAI/bge-m3
+datasets: []
+language: []
+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:9593
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Aquest tràmit permet a la nova persona titular sol·licitar el canvi
+    de nom d'una llicència de gual, sempre que no variïn la utilització ni les característiques
+    de la llicència concedida prèviament, i s’acompleixen les ordenances vigents.
+  sentences:
+  - Quin és el resultat de la presentació del tràmit de comunicació d'inici i modificació
+    substancial d'activitat en un establiment?
+  - Quin és el benefici per a les entitats especialitzades de la gestió delegada?
+  - Necessito canviar el titular de la meva llicència de gual
+- source_sentence: Mitjançant aquest tràmit la persona interessada posa en coneixement
+    de l'Ajuntament l'inici o modificació substancial d'una activitat econòmica, de
+    les incloses en l'annex de la Llei de facilitació de l'activitat econòmica, i
+    hi adjunta el projecte i el certificat tècnic acreditatiu del compliment dels
+    requisits necessaris que estableix la normativa vigent per a l'exercici de l'activitat.
+  sentences:
+  - Quins canvis es poden fer en els tanques?
+  - Què és necessari per gaudir d'exempció de les taxes per recollida d'escombraries?
+  - Quin és el resultat de la presentació del certificat tècnic acreditatiu?
+- source_sentence: La instal·lació i utilització d’una grua torre està subjecta a
+    l’obtenció d’una llicència municipal.
+  sentences:
+  - Quin és el propòsit de la Declaració de baixa de la Taxa pel servei municipal
+    complementari de recollida, tractament i eliminació de residus comercials?
+  - Quin és el paper de la persona beneficiària en el pagament de l'ajut de lloguer
+    just?
+  - Què és necessari per a la instal·lació i utilització d'una grua torre?
+- source_sentence: El procediment d'adjudicació serà mitjançant concurs públic, amb
+    la presentació de la sol·licitud dins del termini establert per cada convocatòria,
+    amb la priorització de casos amb seguiment social i educatiu a persones i famílies
+    en situació de vulnerabilitat social i econòmica.
+  sentences:
+  - Quins són els casos que tenen prioritat en l'adjudicació dels habitatges del Fons
+    d'Habitatges d'Inclusió Social?
+  - Quin és el paper del certificat del nombre d'habitatges en el tràmit d'obertura
+    d'una oficina de farmàcia?
+  - Quin és el paper de la Junta de Govern Local en relació amb les garanties?
+- source_sentence: Els comerciants locals han de sol·licitar els ajuts per al projecte
+    de la targeta de fidelització dins del termini establert per l'Ajuntament de Sitges.
+  sentences:
+  - Quin és el paper de la persona cuidadora en la gestió de les emergències en la
+    colònia felina?
+  - Quin és el termini perquè els comerciants locals puguin sol·licitar els ajuts
+    per al projecte de la targeta de fidelització?
+  - Quin és el règim especial al qual han d'estar inscrites les persones per rebre
+    els ajuts?
+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: 0.0600375234521576
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.1303939962476548
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.1801125703564728
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.32833020637898686
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0600375234521576
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04346466541588492
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.036022514071294566
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03283302063789869
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0600375234521576
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.1303939962476548
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1801125703564728
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.32833020637898686
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16801025559505256
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.12051319276929036
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14641981337897508
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.05909943714821764
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.12195121951219512
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18105065666041276
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3302063789868668
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.05909943714821764
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04065040650406503
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03621013133208256
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03302063789868668
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.05909943714821764
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.12195121951219512
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18105065666041276
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3302063789868668
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.1674921436005172
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.119329044938801
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14541664461952028
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.058161350844277676
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.12851782363977485
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.1904315196998124
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.32645403377110693
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.058161350844277676
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04283927454659161
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03808630393996248
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03264540337711069
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.058161350844277676
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.12851782363977485
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1904315196998124
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.32645403377110693
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16736509943357222
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11985169302242468
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14638786229645445
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.054409005628517824
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.11913696060037524
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18198874296435272
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3170731707317073
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.054409005628517824
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03971232020012507
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.036397748592870545
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03170731707317073
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.054409005628517824
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.11913696060037524
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18198874296435272
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3170731707317073
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16104635688777047
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11454927186634503
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14146334434951485
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.054409005628517824
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.12195121951219512
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18198874296435272
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.31144465290806755
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.054409005628517824
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04065040650406503
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03639774859287054
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.031144465290806757
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.054409005628517824
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.12195121951219512
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18198874296435272
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.31144465290806755
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15963450508596505
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11438361773727633
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14164175280264735
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.05065666041275797
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.11444652908067542
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18292682926829268
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3076923076923077
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.05065666041275797
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0381488430268918
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.036585365853658534
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.030769230769230767
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.05065666041275797
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.11444652908067542
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18292682926829268
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3076923076923077
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.1558660768539628
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11049949373120106
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13758639006498824
+      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). 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:** Unknown -->
+<!-- - **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/sitgrsBAAIbge-m3-300824v2")
+# Run inference
+sentences = [
+    "Els comerciants locals han de sol·licitar els ajuts per al projecte de la targeta de fidelització dins del termini establert per l'Ajuntament de Sitges.",
+    'Quin és el termini perquè els comerciants locals puguin sol·licitar els ajuts per al projecte de la targeta de fidelització?',
+    'Quin és el paper de la persona cuidadora en la gestió de les emergències en la colònia felina?',
+]
+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   | 0.06       |
+| cosine_accuracy@3   | 0.1304     |
+| cosine_accuracy@5   | 0.1801     |
+| cosine_accuracy@10  | 0.3283     |
+| cosine_precision@1  | 0.06       |
+| cosine_precision@3  | 0.0435     |
+| cosine_precision@5  | 0.036      |
+| cosine_precision@10 | 0.0328     |
+| cosine_recall@1     | 0.06       |
+| cosine_recall@3     | 0.1304     |
+| cosine_recall@5     | 0.1801     |
+| cosine_recall@10    | 0.3283     |
+| cosine_ndcg@10      | 0.168      |
+| cosine_mrr@10       | 0.1205     |
+| **cosine_map@100**  | **0.1464** |
+
+#### 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   | 0.0591     |
+| cosine_accuracy@3   | 0.122      |
+| cosine_accuracy@5   | 0.1811     |
+| cosine_accuracy@10  | 0.3302     |
+| cosine_precision@1  | 0.0591     |
+| cosine_precision@3  | 0.0407     |
+| cosine_precision@5  | 0.0362     |
+| cosine_precision@10 | 0.033      |
+| cosine_recall@1     | 0.0591     |
+| cosine_recall@3     | 0.122      |
+| cosine_recall@5     | 0.1811     |
+| cosine_recall@10    | 0.3302     |
+| cosine_ndcg@10      | 0.1675     |
+| cosine_mrr@10       | 0.1193     |
+| **cosine_map@100**  | **0.1454** |
+
+#### 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   | 0.0582     |
+| cosine_accuracy@3   | 0.1285     |
+| cosine_accuracy@5   | 0.1904     |
+| cosine_accuracy@10  | 0.3265     |
+| cosine_precision@1  | 0.0582     |
+| cosine_precision@3  | 0.0428     |
+| cosine_precision@5  | 0.0381     |
+| cosine_precision@10 | 0.0326     |
+| cosine_recall@1     | 0.0582     |
+| cosine_recall@3     | 0.1285     |
+| cosine_recall@5     | 0.1904     |
+| cosine_recall@10    | 0.3265     |
+| cosine_ndcg@10      | 0.1674     |
+| cosine_mrr@10       | 0.1199     |
+| **cosine_map@100**  | **0.1464** |
+
+#### 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   | 0.0544     |
+| cosine_accuracy@3   | 0.1191     |
+| cosine_accuracy@5   | 0.182      |
+| cosine_accuracy@10  | 0.3171     |
+| cosine_precision@1  | 0.0544     |
+| cosine_precision@3  | 0.0397     |
+| cosine_precision@5  | 0.0364     |
+| cosine_precision@10 | 0.0317     |
+| cosine_recall@1     | 0.0544     |
+| cosine_recall@3     | 0.1191     |
+| cosine_recall@5     | 0.182      |
+| cosine_recall@10    | 0.3171     |
+| cosine_ndcg@10      | 0.161      |
+| cosine_mrr@10       | 0.1145     |
+| **cosine_map@100**  | **0.1415** |
+
+#### 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   | 0.0544     |
+| cosine_accuracy@3   | 0.122      |
+| cosine_accuracy@5   | 0.182      |
+| cosine_accuracy@10  | 0.3114     |
+| cosine_precision@1  | 0.0544     |
+| cosine_precision@3  | 0.0407     |
+| cosine_precision@5  | 0.0364     |
+| cosine_precision@10 | 0.0311     |
+| cosine_recall@1     | 0.0544     |
+| cosine_recall@3     | 0.122      |
+| cosine_recall@5     | 0.182      |
+| cosine_recall@10    | 0.3114     |
+| cosine_ndcg@10      | 0.1596     |
+| cosine_mrr@10       | 0.1144     |
+| **cosine_map@100**  | **0.1416** |
+
+#### 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   | 0.0507     |
+| cosine_accuracy@3   | 0.1144     |
+| cosine_accuracy@5   | 0.1829     |
+| cosine_accuracy@10  | 0.3077     |
+| cosine_precision@1  | 0.0507     |
+| cosine_precision@3  | 0.0381     |
+| cosine_precision@5  | 0.0366     |
+| cosine_precision@10 | 0.0308     |
+| cosine_recall@1     | 0.0507     |
+| cosine_recall@3     | 0.1144     |
+| cosine_recall@5     | 0.1829     |
+| cosine_recall@10    | 0.3077     |
+| cosine_ndcg@10      | 0.1559     |
+| cosine_mrr@10       | 0.1105     |
+| **cosine_map@100**  | **0.1376** |
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+
+* Size: 9,593 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: 49.72 tokens</li><li>max: 190 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 21.22 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                           | anchor                                                                                                  |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------|
+  | <code>Mitjançant aquest tràmit la persona interessada posa en coneixement de l'Ajuntament l’inici o modificació substancial d’una activitat econòmica.</code>      | <code>Quin és el paper de l'Ajuntament en la comunicació de modificació d'activitat?</code>             |
+  | <code>El Carnet Blau és un carnet personal i intransferible que acredita el compliment dels requisits per a gaudir d'un conjunt de descomptes i avantatges.</code> | <code>Quin és el propòsit del Carnet Blau en relació amb els descomptes?</code>                         |
+  | <code>Bonificació del 25% de l'import corresponent al consum d'aigua, la conservació d'escomeses, aforaments i comptadors així com els drets de connexió.</code>   | <code>Quin és l'objectiu de la bonificació de la taxa per distribució i subministrament d'aigua?</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`: 10
+- `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`: 10
+- `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 |
+|:----------:|:-------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.2667     | 10      | 3.4587        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.5333     | 20      | 2.8693        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.8        | 30      | 2.3094        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.9867     | 37      | -             | 0.1331                  | 0.1252                 | 0.1322                 | 0.1337                 | 0.1128                | 0.1347                 |
+| 1.0667     | 40      | 1.6196        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.3333     | 50      | 1.1926        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.6        | 60      | 0.9497        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.8667     | 70      | 0.882         | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.0        | 75      | -             | 0.1372                  | 0.1272                 | 0.1298                 | 0.1365                 | 0.1212                | 0.1369                 |
+| 2.1333     | 80      | 0.5621        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.4        | 90      | 0.4454        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.6667     | 100     | 0.4143        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.9333     | 110     | 0.4014        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.9867     | 112     | -             | 0.1365                  | 0.1282                 | 0.1329                 | 0.1437                 | 0.1259                | 0.1390                 |
+| 3.2        | 120     | 0.2863        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.4667     | 130     | 0.1977        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.7333     | 140     | 0.2411        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.0        | 150     | 0.222         | 0.1355                  | 0.1308                 | 0.1378                 | 0.1346                 | 0.1239                | 0.1362                 |
+| 4.2667     | 160     | 0.1705        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.5333     | 170     | 0.1522        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.8        | 180     | 0.1606        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.9867     | 187     | -             | 0.1441                  | 0.1305                 | 0.1344                 | 0.1373                 | 0.1356                | 0.1409                 |
+| 5.0667     | 190     | 0.1281        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 5.3333     | 200     | 0.1099        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 5.6        | 210     | 0.0921        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 5.8667     | 220     | 0.114         | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.0        | 225     | -             | 0.1371                  | 0.1361                 | 0.1331                 | 0.1371                 | 0.1351                | 0.1421                 |
+| 6.1333     | 230     | 0.0703        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.4        | 240     | 0.0746        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.6667     | 250     | 0.0734        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.9333     | 260     | 0.0803        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.9867     | 262     | -             | 0.1447                  | 0.1400                 | 0.1422                 | 0.1397                 | 0.1376                | 0.1395                 |
+| 7.2        | 270     | 0.0684        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 7.4667     | 280     | 0.0493        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 7.7333     | 290     | 0.0531        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 8.0        | 300     | 0.0705        | 0.1410                  | 0.1411                 | 0.1379                 | 0.1372                 | 0.1372                | 0.1380                 |
+| 8.2667     | 310     | 0.0495        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 8.5333     | 320     | 0.0478        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 8.8        | 330     | 0.0455        | -                       | -                      | -                      | -                      | -                     | -                      |
+| **8.9867** | **337** | **-**         | **0.1463**              | **0.1456**             | **0.1416**             | **0.1445**             | **0.1408**            | **0.1427**             |
+| 9.0667     | 340     | 0.0495        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 9.3333     | 350     | 0.0457        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 9.6        | 360     | 0.0487        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 9.8667     | 370     | 0.0568        | 0.1464                  | 0.1416                 | 0.1415                 | 0.1464                 | 0.1376                | 0.1454                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.34.0.dev0
+- Datasets: 2.21.0
+- 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": "3.0.1",
+    "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:f27851c4cd7344e61094592776ff3711abfcb0b90964d33096a8c78147f57414
+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>"
+}