Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,1017 @@
+---
+language:
+- es
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:14907
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: jinaai/jina-embeddings-v3
+widget:
+- source_sentence: Describe la tradición del 'rosario de candiles' en el contexto
+    de la minería.
+  sentences:
+  - Un mechazo es la combustión de la mecha sin que se llegue a inflamar el barreno.
+  - La siega tradicional en Escucha comenzaba antes de San Juan con las cebadas.
+  - El 'rosario de candiles' es una tradición religiosa celebrada en la festividad
+    de San Juan, en la que los mineros escuchan y acompañan con sus candiles de carburo,
+    rezando a dos coros y cantando en parte.
+- source_sentence: ¿Qué significa la expresión 'pillar una mojadina'?
+  sentences:
+  - En el campeonato provincial de atletismo en Alcorisa en mayo, Pilar Brumos de
+    Escucha logró la 3ª posición en 600 metros y el subcampeonato en peso.
+  - Los empresarios de Escucha se habían unido para poder participar en las elecciones
+    a CC.PP. ya que era necesario que la plantilla de la empresa superase el número
+    de 50 trabajadores..
+  - '''Pillar una mojadina'' significa empaparse, quedar empapado.'
+- source_sentence: ¿En qué año Carbones de Teruel registra la mina 'pablo' en Escucha?
+  sentences:
+  - Puede referirse a un calcetín para bebés o a un calcetín gordo.
+  - Carbones de Teruel registra la mina 'pablo' en Escucha en 1900.
+  - 'Jesús Conesa explicó a la Junta de Espectáculos que el anterior propietario,
+    Sr. Latorre Galindo, tenía otro cine en Utrillas, lo que causaba continuos equívocos
+    en envíos de material y pagos, al creerse que ambos cines le pertenecían o eran
+    la misma empresa. '
+- source_sentence: ¿Quién regentaba el Cine Avenida de Escucha en el momento de su
+    cierre?
+  sentences:
+  - Se usa con el significado de 'cuando'.
+  - El CD Escucha alineó a Castillo, Romero, Bobadilla, Moraleda, Luis, González,
+    Higinio, Torres, Calomarde I, Calomarde II y Navarro en el partido de Copa contra
+    el Alcorisa.
+  - Antonio Malpica regentaba el Cine Avenida de Escucha en el momento de su cierre.
+- source_sentence: ¿Qué porcentaje de aumento salarial reclamaba el Sindicato Minero
+    en el conflicto de Utrillas que llevó a plantear la huelga del 12 de octubre de
+    1930?
+  sentences:
+  - Antonio Gargallo.
+  - Una publicación con una fotografía para el recuerdo de la locomotora llamada 'Escucha'.
+  - El Sindicato Minero reclamaba un aumento del 20% los sueldos en el conflicto de
+    Utrillas.
+pipeline_tag: sentence-similarity
+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
+model-index:
+- name: Lampistero
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.771876885938443
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8931804465902233
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9136994568497284
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.928183464091732
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.771876885938443
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2977268155300744
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18273989136994565
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0928183464091732
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.771876885938443
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8931804465902233
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9136994568497284
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.928183464091732
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8567624282543636
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8330754087996087
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8344062726339423
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7706698853349426
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8925769462884732
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9118889559444779
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9287869643934822
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7706698853349426
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2975256487628244
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18237779118889558
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09287869643934822
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7706698853349426
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8925769462884732
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9118889559444779
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9287869643934822
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8563506024476554
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8323629431655981
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8335898787409641
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7682558841279421
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.891973445986723
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9106819553409776
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9299939649969825
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7682558841279421
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2973244819955743
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1821363910681955
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09299939649969825
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7682558841279421
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.891973445986723
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9106819553409776
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9299939649969825
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8553875428985249
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8307586381967789
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8318464309684749
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7646348823174411
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8883524441762221
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9058539529269765
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9251659625829813
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7646348823174411
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.296117481392074
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18117079058539529
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09251659625829814
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7646348823174411
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8883524441762221
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9058539529269765
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9251659625829813
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8515592939892533
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.827186251688363
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8285316886087458
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7531683765841883
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8774894387447194
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8968014484007242
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9161134580567291
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7531683765841883
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2924964795815731
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17936028968014484
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09161134580567289
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7531683765841883
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8774894387447194
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8968014484007242
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9161134580567291
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8412352149980756
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8165177074652028
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8182055440879425
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7109233554616777
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8503319251659626
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8750754375377188
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8974049487024743
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7109233554616777
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2834439750553209
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17501508750754374
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08974049487024743
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7109233554616777
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8503319251659626
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8750754375377188
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8974049487024743
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8110786488208866
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7826713988753816
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7847527919142971
+      name: Cosine Map@100
+---
+
+# Lampistero
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [jinaai/jina-embeddings-v3](https://huggingface.co/jinaai/jina-embeddings-v3) 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:** [jinaai/jina-embeddings-v3](https://huggingface.co/jinaai/jina-embeddings-v3) <!-- at revision f1944de8402dcd5f2b03f822a4bc22a7f2de2eb9 -->
+- **Maximum Sequence Length:** 8194 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** es
+- **License:** apache-2.0
+
+### 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(
+  (transformer): Transformer(
+    (auto_model): XLMRobertaLoRA(
+      (roberta): XLMRobertaModel(
+        (embeddings): XLMRobertaEmbeddings(
+          (word_embeddings): ParametrizedEmbedding(
+            250002, 1024, padding_idx=1
+            (parametrizations): ModuleDict(
+              (weight): ParametrizationList(
+                (0): LoRAParametrization()
+              )
+            )
+          )
+          (token_type_embeddings): ParametrizedEmbedding(
+            1, 1024
+            (parametrizations): ModuleDict(
+              (weight): ParametrizationList(
+                (0): LoRAParametrization()
+              )
+            )
+          )
+        )
+        (emb_drop): Dropout(p=0.1, inplace=False)
+        (emb_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+        (encoder): XLMRobertaEncoder(
+          (layers): ModuleList(
+            (0-23): 24 x Block(
+              (mixer): MHA(
+                (rotary_emb): RotaryEmbedding()
+                (Wqkv): ParametrizedLinearResidual(
+                  in_features=1024, out_features=3072, bias=True
+                  (parametrizations): ModuleDict(
+                    (weight): ParametrizationList(
+                      (0): LoRAParametrization()
+                    )
+                  )
+                )
+                (inner_attn): FlashSelfAttention(
+                  (drop): Dropout(p=0.1, inplace=False)
+                )
+                (inner_cross_attn): FlashCrossAttention(
+                  (drop): Dropout(p=0.1, inplace=False)
+                )
+                (out_proj): ParametrizedLinear(
+                  in_features=1024, out_features=1024, bias=True
+                  (parametrizations): ModuleDict(
+                    (weight): ParametrizationList(
+                      (0): LoRAParametrization()
+                    )
+                  )
+                )
+              )
+              (dropout1): Dropout(p=0.1, inplace=False)
+              (drop_path1): StochasticDepth(p=0.0, mode=row)
+              (norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): ParametrizedLinear(
+                  in_features=1024, out_features=4096, bias=True
+                  (parametrizations): ModuleDict(
+                    (weight): ParametrizationList(
+                      (0): LoRAParametrization()
+                    )
+                  )
+                )
+                (fc2): ParametrizedLinear(
+                  in_features=4096, out_features=1024, bias=True
+                  (parametrizations): ModuleDict(
+                    (weight): ParametrizationList(
+                      (0): LoRAParametrization()
+                    )
+                  )
+                )
+              )
+              (dropout2): Dropout(p=0.1, inplace=False)
+              (drop_path2): StochasticDepth(p=0.0, mode=row)
+              (norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+            )
+          )
+        )
+        (pooler): XLMRobertaPooler(
+          (dense): ParametrizedLinear(
+            in_features=1024, out_features=1024, bias=True
+            (parametrizations): ModuleDict(
+              (weight): ParametrizationList(
+                (0): LoRAParametrization()
+              )
+            )
+          )
+          (activation): Tanh()
+        )
+      )
+    )
+  )
+  (pooler): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (normalizer): 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("csanz91/lampistero_rag_embeddings")
+# Run inference
+sentences = [
+    '¿Qué porcentaje de aumento salarial reclamaba el Sindicato Minero en el conflicto de Utrillas que llevó a plantear la huelga del 12 de octubre de 1930?',
+    'El Sindicato Minero reclamaba un aumento del 20% los sueldos en el conflicto de Utrillas.',
+    'Antonio Gargallo.',
+]
+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) with these parameters:
+  ```json
+  {
+      "truncate_dim": 1024
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7719     |
+| cosine_accuracy@3   | 0.8932     |
+| cosine_accuracy@5   | 0.9137     |
+| cosine_accuracy@10  | 0.9282     |
+| cosine_precision@1  | 0.7719     |
+| cosine_precision@3  | 0.2977     |
+| cosine_precision@5  | 0.1827     |
+| cosine_precision@10 | 0.0928     |
+| cosine_recall@1     | 0.7719     |
+| cosine_recall@3     | 0.8932     |
+| cosine_recall@5     | 0.9137     |
+| cosine_recall@10    | 0.9282     |
+| **cosine_ndcg@10**  | **0.8568** |
+| cosine_mrr@10       | 0.8331     |
+| cosine_map@100      | 0.8344     |
+
+#### Information Retrieval
+
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7707     |
+| cosine_accuracy@3   | 0.8926     |
+| cosine_accuracy@5   | 0.9119     |
+| cosine_accuracy@10  | 0.9288     |
+| cosine_precision@1  | 0.7707     |
+| cosine_precision@3  | 0.2975     |
+| cosine_precision@5  | 0.1824     |
+| cosine_precision@10 | 0.0929     |
+| cosine_recall@1     | 0.7707     |
+| cosine_recall@3     | 0.8926     |
+| cosine_recall@5     | 0.9119     |
+| cosine_recall@10    | 0.9288     |
+| **cosine_ndcg@10**  | **0.8564** |
+| cosine_mrr@10       | 0.8324     |
+| cosine_map@100      | 0.8336     |
+
+#### Information Retrieval
+
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7683     |
+| cosine_accuracy@3   | 0.892      |
+| cosine_accuracy@5   | 0.9107     |
+| cosine_accuracy@10  | 0.93       |
+| cosine_precision@1  | 0.7683     |
+| cosine_precision@3  | 0.2973     |
+| cosine_precision@5  | 0.1821     |
+| cosine_precision@10 | 0.093      |
+| cosine_recall@1     | 0.7683     |
+| cosine_recall@3     | 0.892      |
+| cosine_recall@5     | 0.9107     |
+| cosine_recall@10    | 0.93       |
+| **cosine_ndcg@10**  | **0.8554** |
+| cosine_mrr@10       | 0.8308     |
+| cosine_map@100      | 0.8318     |
+
+#### Information Retrieval
+
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7646     |
+| cosine_accuracy@3   | 0.8884     |
+| cosine_accuracy@5   | 0.9059     |
+| cosine_accuracy@10  | 0.9252     |
+| cosine_precision@1  | 0.7646     |
+| cosine_precision@3  | 0.2961     |
+| cosine_precision@5  | 0.1812     |
+| cosine_precision@10 | 0.0925     |
+| cosine_recall@1     | 0.7646     |
+| cosine_recall@3     | 0.8884     |
+| cosine_recall@5     | 0.9059     |
+| cosine_recall@10    | 0.9252     |
+| **cosine_ndcg@10**  | **0.8516** |
+| cosine_mrr@10       | 0.8272     |
+| cosine_map@100      | 0.8285     |
+
+#### Information Retrieval
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7532     |
+| cosine_accuracy@3   | 0.8775     |
+| cosine_accuracy@5   | 0.8968     |
+| cosine_accuracy@10  | 0.9161     |
+| cosine_precision@1  | 0.7532     |
+| cosine_precision@3  | 0.2925     |
+| cosine_precision@5  | 0.1794     |
+| cosine_precision@10 | 0.0916     |
+| cosine_recall@1     | 0.7532     |
+| cosine_recall@3     | 0.8775     |
+| cosine_recall@5     | 0.8968     |
+| cosine_recall@10    | 0.9161     |
+| **cosine_ndcg@10**  | **0.8412** |
+| cosine_mrr@10       | 0.8165     |
+| cosine_map@100      | 0.8182     |
+
+#### Information Retrieval
+
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7109     |
+| cosine_accuracy@3   | 0.8503     |
+| cosine_accuracy@5   | 0.8751     |
+| cosine_accuracy@10  | 0.8974     |
+| cosine_precision@1  | 0.7109     |
+| cosine_precision@3  | 0.2834     |
+| cosine_precision@5  | 0.175      |
+| cosine_precision@10 | 0.0897     |
+| cosine_recall@1     | 0.7109     |
+| cosine_recall@3     | 0.8503     |
+| cosine_recall@5     | 0.8751     |
+| cosine_recall@10    | 0.8974     |
+| **cosine_ndcg@10**  | **0.8111** |
+| cosine_mrr@10       | 0.7827     |
+| cosine_map@100      | 0.7848     |
+
+<!--
+## 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: 14,907 training samples
+* Columns: <code>query</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | answer                                                                             |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 25.88 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 34.09 tokens</li><li>max: 340 tokens</li></ul> |
+* Samples:
+  | query                                                                                       | answer                                                                                                                     |
+  |:--------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|
+  | <code>En Valdeconejos, ¿cuál era la sociedad de agricultores en 1952?</code>                | <code>En Valdeconejos, la sociedad de agricultores en 1952 era el Pósito de Agricultores.</code>                           |
+  | <code>¿Qué nombres de capataces se registran en el pueblo de Escucha en el año 1952?</code> | <code>En Escucha, en 1952, los capataces registrados son Peralta (Manuel) y Rodriguez (Gonzalo).</code>                    |
+  | <code>En el contexto de la minería, ¿qué implica 'despajar'?</code>                         | <code>'Despajar' se refiere a cribar a mano material y desechos para obtener las partes de carbón que hay en ellos.</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`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `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`: 32
+- `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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: 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}
+- `tp_size`: 0
+- `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`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | dim_1024_cosine_ndcg@10 | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.3433 | 10   | 23.532        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.6867 | 20   | 10.6294       | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.0    | 30   | 5.9964        | 0.8436                  | 0.8428                 | 0.8417                 | 0.8373                 | 0.8254                 | 0.7920                |
+| 1.3433 | 40   | 4.451         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.6867 | 50   | 4.7053        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.0    | 60   | 3.9423        | 0.8555                  | 0.8539                 | 0.8535                 | 0.8505                 | 0.8374                 | 0.8075                |
+| 2.3433 | 70   | 4.0009        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.6867 | 80   | 4.3913        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.0    | 90   | 2.9362        | 0.8566                  | 0.8548                 | 0.8554                 | 0.8514                 | 0.8401                 | 0.8089                |
+| 3.3433 | 100  | 3.7804        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.6867 | 110  | 4.5676        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.8927 | 116  | -             | 0.8568                  | 0.8564                 | 0.8554                 | 0.8516                 | 0.8412                 | 0.8111                |
+
+
+### Framework Versions
+- Python: 3.12.10
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.7.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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 +1,66 @@
+{
+  "architectures": [
+    "XLMRobertaLoRA"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "jinaai/xlm-roberta-flash-implementation--configuration_xlm_roberta.XLMRobertaFlashConfig",
+    "AutoModel": "jinaai/xlm-roberta-flash-implementation--modeling_lora.XLMRobertaLoRA",
+    "AutoModelForMaskedLM": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForMaskedLM",
+    "AutoModelForPreTraining": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForPreTraining"
+  },
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "emb_pooler": 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,
+  "load_trained_adapters": true,
+  "lora_adaptations": [
+    "retrieval.query",
+    "retrieval.passage",
+    "separation",
+    "classification",
+    "text-matching"
+  ],
+  "lora_alpha": 1,
+  "lora_dropout_p": 0.0,
+  "lora_main_params_trainable": true,
+  "lora_rank": 4,
+  "matryoshka_dimensions": [
+    32,
+    64,
+    128,
+    256,
+    512,
+    768,
+    1024
+  ],
+  "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": "rotary",
+  "rotary_emb_base": 20000.0,
+  "task_instructions": {
+    "classification": "",
+    "retrieval.passage": "Represent the document for retrieval: ",
+    "retrieval.query": "Represent the query for retrieving evidence documents: ",
+    "separation": "",
+    "text-matching": ""
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "truncate_dim": null,
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_flash_attn": true,
+  "use_reentrant": false,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,16 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {
+    "retrieval.query": "Represent the query for retrieving evidence documents: ",
+    "retrieval.passage": "Represent the document for retrieval: ",
+    "separation": "",
+    "classification": "",
+    "text-matching": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

custom_st.py

@@ -0,0 +1,229 @@
+import json
+import logging
+import os
+from io import BytesIO
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import torch
+from torch import nn
+from transformers import AutoConfig, AutoModel, AutoTokenizer
+
+logger = logging.getLogger(__name__)
+
+
+class Transformer(nn.Module):
+    """Huggingface AutoModel to generate token embeddings.
+    Loads the correct class, e.g. BERT / RoBERTa etc.
+
+    Args:
+        model_name_or_path: Huggingface models name
+            (https://huggingface.co/models)
+        max_seq_length: Truncate any inputs longer than max_seq_length
+        model_args: Keyword arguments passed to the Huggingface
+            Transformers model
+        tokenizer_args: Keyword arguments passed to the Huggingface
+            Transformers tokenizer
+        config_args: Keyword arguments passed to the Huggingface
+            Transformers config
+        cache_dir: Cache dir for Huggingface Transformers to store/load
+            models
+        do_lower_case: If true, lowercases the input (independent if the
+            model is cased or not)
+        tokenizer_name_or_path: Name or path of the tokenizer. When
+            None, then model_name_or_path is used
+    """
+
+    save_in_root: bool = True
+
+    def __init__(
+        self,
+        model_name_or_path: str,
+        max_seq_length: int = None,
+        model_args: Dict[str, Any] = None,
+        tokenizer_args: Dict[str, Any] = None,
+        config_args: Dict[str, Any] = None,
+        cache_dir: str = None,
+        do_lower_case: bool = False,
+        tokenizer_name_or_path: str = None,
+        **kwargs,
+    ) -> None:
+        super().__init__()
+        self.config_keys = ["max_seq_length", "do_lower_case"]
+        self.do_lower_case = do_lower_case
+        if model_args is None:
+            model_args = {}
+        if tokenizer_args is None:
+            tokenizer_args = {}
+        if config_args is None:
+            config_args = {}
+
+        if kwargs.get("backend", "torch") != "torch":
+            logger.warning(
+                f'"jinaai/jina-embeddings-v3" is currently not compatible with the {kwargs["backend"]} backend. '
+                'Continuing with the "torch" backend.'
+            )
+        
+        self.config = AutoConfig.from_pretrained(model_name_or_path, **config_args, cache_dir=cache_dir)
+
+        self._lora_adaptations = self.config.lora_adaptations
+        if (
+            not isinstance(self._lora_adaptations, list)
+            or len(self._lora_adaptations) < 1
+        ):
+            raise ValueError(
+                f"`lora_adaptations` must be a list and contain at least one element"
+            )
+        self._adaptation_map = {
+            name: idx for idx, name in enumerate(self._lora_adaptations)
+        }
+
+        self.default_task = model_args.pop('default_task', None)
+
+        self.auto_model = AutoModel.from_pretrained(model_name_or_path, config=self.config, cache_dir=cache_dir, **model_args)
+
+        if max_seq_length is not None and "model_max_length" not in tokenizer_args:
+            tokenizer_args["model_max_length"] = max_seq_length
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            tokenizer_name_or_path if tokenizer_name_or_path is not None else model_name_or_path,
+            cache_dir=cache_dir,
+            **tokenizer_args,
+        )
+
+        # No max_seq_length set. Try to infer from model
+        if max_seq_length is None:
+            if (
+                hasattr(self.auto_model, "config")
+                and hasattr(self.auto_model.config, "max_position_embeddings")
+                and hasattr(self.tokenizer, "model_max_length")
+            ):
+                max_seq_length = min(self.auto_model.config.max_position_embeddings, self.tokenizer.model_max_length)
+
+        self.max_seq_length = max_seq_length
+
+        if tokenizer_name_or_path is not None:
+            self.auto_model.config.tokenizer_class = self.tokenizer.__class__.__name__
+
+
+    @property
+    def default_task(self):
+        return self._default_task
+
+    @default_task.setter
+    def default_task(self, task: Union[None, str]):
+        self._validate_task(task)
+        self._default_task = task
+        
+
+    def _validate_task(self, task: str):
+        if task and task not in self._lora_adaptations:
+            raise ValueError(
+                f"Unsupported task '{task}'. "
+                f"Supported tasks are: {', '.join(self.config.lora_adaptations)}. "
+                f"Alternatively, don't pass the `task` argument to disable LoRA."
+            )
+
+    def forward(
+        self, features: Dict[str, torch.Tensor], task: Optional[str] = None
+    ) -> Dict[str, torch.Tensor]:
+        """Returns token_embeddings, cls_token"""
+        self._validate_task(task)
+        task = task or self.default_task
+        adapter_mask = None
+        if task:
+            task_id = self._adaptation_map[task]
+            num_examples = features['input_ids'].size(0)
+            adapter_mask = torch.full(
+                (num_examples,), task_id, dtype=torch.int32, device=features['input_ids'].device
+            )
+
+        lora_arguments = (
+            {"adapter_mask": adapter_mask} if adapter_mask is not None else {}
+        )
+        features.pop('prompt_length', None)
+        output_states = self.auto_model.forward(**features, **lora_arguments, return_dict=False)
+        output_tokens = output_states[0]
+        features.update({"token_embeddings": output_tokens, "attention_mask": features["attention_mask"]})
+        return features
+
+    def get_word_embedding_dimension(self) -> int:
+        return self.auto_model.config.hidden_size
+
+    def tokenize(
+        self,
+        texts: Union[List[str], List[dict], List[Tuple[str, str]]],
+        padding: Union[str, bool] = True
+    ) -> Dict[str, torch.Tensor]:
+        """Tokenizes a text and maps tokens to token-ids"""
+        output = {}
+        if isinstance(texts[0], str):
+            to_tokenize = [texts]
+        elif isinstance(texts[0], dict):
+            to_tokenize = []
+            output["text_keys"] = []
+            for lookup in texts:
+                text_key, text = next(iter(lookup.items()))
+                to_tokenize.append(text)
+                output["text_keys"].append(text_key)
+            to_tokenize = [to_tokenize]
+        else:
+            batch1, batch2 = [], []
+            for text_tuple in texts:
+                batch1.append(text_tuple[0])
+                batch2.append(text_tuple[1])
+            to_tokenize = [batch1, batch2]
+
+        # strip
+        to_tokenize = [[str(s).strip() for s in col] for col in to_tokenize]
+
+        # Lowercase
+        if self.do_lower_case:
+            to_tokenize = [[s.lower() for s in col] for col in to_tokenize]
+
+        output.update(
+            self.tokenizer(
+                *to_tokenize,
+                padding=padding,
+                truncation="longest_first",
+                return_tensors="pt",
+                max_length=self.max_seq_length,
+            )
+        )
+        return output
+
+    def get_config_dict(self) -> Dict[str, Any]:
+         return {key: self.__dict__[key] for key in self.config_keys}
+
+    def save(self, output_path: str, safe_serialization: bool = True) -> None:
+        self.auto_model.save_pretrained(output_path, safe_serialization=safe_serialization)
+        self.tokenizer.save_pretrained(output_path)
+
+        with open(os.path.join(output_path, "sentence_bert_config.json"), "w") as fOut:
+            json.dump(self.get_config_dict(), fOut, indent=2)
+
+
+    @classmethod
+    def load(cls, input_path: str) -> "Transformer":
+        # Old classes used other config names than 'sentence_bert_config.json'
+        for config_name in [
+            "sentence_bert_config.json",
+            "sentence_roberta_config.json",
+            "sentence_distilbert_config.json",
+            "sentence_camembert_config.json",
+            "sentence_albert_config.json",
+            "sentence_xlm-roberta_config.json",
+            "sentence_xlnet_config.json",
+        ]:
+            sbert_config_path = os.path.join(input_path, config_name)
+            if os.path.exists(sbert_config_path):
+                break
+
+        with open(sbert_config_path) as fIn:
+            config = json.load(fIn)
+        # Don't allow configs to set trust_remote_code
+        if "model_args" in config and "trust_remote_code" in config["model_args"]:
+            config["model_args"].pop("trust_remote_code")
+        if "tokenizer_args" in config and "trust_remote_code" in config["tokenizer_args"]:
+            config["tokenizer_args"].pop("trust_remote_code")
+        if "config_args" in config and "trust_remote_code" in config["config_args"]:
+            config["config_args"].pop("trust_remote_code")
+        return cls(model_name_or_path=input_path, **config)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77438c542b0993994f69a4e6c0cf7341c8024b647f3fe764660ad9e6696aaad9
+size 1144685320

modules.json

@@ -0,0 +1,23 @@
+[
+  {
+    "idx": 0,
+    "name": "transformer",
+    "path": "",
+    "type": "custom_st.Transformer",
+    "kwargs": [
+      "task"
+    ]
+  },
+  {
+    "idx": 1,
+    "name": "pooler",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "normalizer",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8194,
+  "do_lower_case": false
+}

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 sha256:3e19cd8c08f528b481e909f73dbd1fd62b1e8b1117579ba205e477801237f9e0
+size 17082988

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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8194,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "unk_token": "<unk>"
+}