Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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 +1,556 @@
+---
+language:
+- en
+- ca
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:1K<n<10K
+- loss:CoSENTLoss
+base_model: microsoft/mpnet-base
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Dia Internacional del Nen Prematur
+  sentences:
+  - Premiats a les comarques de Barcelona
+  - Les concordances són adjectiu / substantiu o verb / substantiu.
+  - Els Mossos en busquen un altre, que va aconseguir fugir en ser enxampats 'in fraganti'
+- source_sentence: Vulneració del dret a la llibertat
+  sentences:
+  - Vulneració del dret a un jutge imparcial
+  - Detenen un home a Malgrat de Mar per apallissar un escombriaire
+  - La víctima ha rebut un cop de puny i ha caigut a terra inconscient
+- source_sentence: Agafem un taxi i ens plantem allà.
+  sentences:
+  - És una activitat gratuïta oberta al públic general.
+  - El líder del PSC, Miquel Iceta, serà el nou president del Senat
+  - El PSOE ja no descarta l’aplicació de l’article 155 de la Constitució a Catalunya
+- source_sentence: No ho entenc, però és el que hi ha.
+  sentences:
+  - és dels plats que a casa ens encanten!
+  - El Punt d'Informació Juvenil és el servei més actiu del centre.
+  - Puigdemont reunirà dimecres a Bèlgica els diputats de JxCat
+- source_sentence: Però que hi ha de cert en tot això?
+  sentences:
+  - Però, què hi ha de veritat en tot això?
+  - Els camioners dissolen la marxa lenta a les rondes de Barcelona
+  - El 112 atén 747.730 trucades durant el primer semestre, un 9,6% més que l'any
+    passat
+pipeline_tag: sentence-similarity
+model-index:
+- name: MPNet base trained on semantic text similarity
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: pearson_cosine
+      value: 0.9369799393019737
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.991833254558149
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9582116235734125
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.9876060961452328
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9594231143506534
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.9887559900790531
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9469313911363318
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.9834282009396937
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9594231143506534
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.991833254558149
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.5855972037779524
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5854785473306573
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.5881281979560977
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.578667646485271
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.5851079475768374
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.5754637407144132
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5612927132777441
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5630862098985
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.5881281979560977
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.5854785473306573
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.6501162382185041
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6819594226888658
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6517756634326819
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6701084565797553
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6553647425414415
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.675292747578234
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6350099608995957
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6458150666120989
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6553647425414415
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6819594226888658
+      name: Spearman Max
+---
+
+# MPNet base trained on semantic text similarity
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca) dataset. It maps sentences & paragraphs to a 768-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:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca)
+- **Languages:** en, ca
+- **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(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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})
+)
+```
+
+## 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("pauhidalgoo/finetuned-sts-ca-mpnet-base")
+# Run inference
+sentences = [
+    'Però que hi ha de cert en tot això?',
+    'Però, què hi ha de veritat en tot això?',
+    'Els camioners dissolen la marxa lenta a les rondes de Barcelona',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.937      |
+| **spearman_cosine** | **0.9918** |
+| pearson_manhattan   | 0.9582     |
+| spearman_manhattan  | 0.9876     |
+| pearson_euclidean   | 0.9594     |
+| spearman_euclidean  | 0.9888     |
+| pearson_dot         | 0.9469     |
+| spearman_dot        | 0.9834     |
+| pearson_max         | 0.9594     |
+| spearman_max        | 0.9918     |
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.5856     |
+| **spearman_cosine** | **0.5855** |
+| pearson_manhattan   | 0.5881     |
+| spearman_manhattan  | 0.5787     |
+| pearson_euclidean   | 0.5851     |
+| spearman_euclidean  | 0.5755     |
+| pearson_dot         | 0.5613     |
+| spearman_dot        | 0.5631     |
+| pearson_max         | 0.5881     |
+| spearman_max        | 0.5855     |
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.6501    |
+| **spearman_cosine** | **0.682** |
+| pearson_manhattan   | 0.6518    |
+| spearman_manhattan  | 0.6701    |
+| pearson_euclidean   | 0.6554    |
+| spearman_euclidean  | 0.6753    |
+| pearson_dot         | 0.635     |
+| spearman_dot        | 0.6458    |
+| pearson_max         | 0.6554    |
+| spearman_max        | 0.682     |
+
+<!--
+## 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
+
+#### projecte-aina/sts-ca
+
+* Dataset: [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca)
+* Size: 2,073 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          | label                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                          |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 32.36 tokens</li><li>max: 82 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 30.57 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.56</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                            | sentence2                                                                                                                                                            | label                           |
+  |:-------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>Atorga per primer cop les mencions Encarna Sanahuja a la inclusió de la perspectiva de gènere en docència Universitària</code> | <code>Creen la menció M. Encarna Sanahuja a la inclusió de la perspectiva de gènere en docència universitària</code>                                                 | <code>3.5</code>                |
+  | <code>Finalment, afegiu-hi els bolets que haureu saltat en una paella amb oli i deixeu-ho coure tot junt durant 5 minuts.</code>     | <code>Finalment, poseu-hi les minipastanagues tallades a dauets, els pèsols, rectifiqueu-ho de sal i deixeu-ho coure tot junt durant un parell de minuts més.</code> | <code>1.25</code>               |
+  | <code>El TC suspèn el pla d'acció exterior i de relacions amb la UE de la Generalitat</code>                                         | <code>El Constitucional manté la suspensió del pla estratègic d'acció exterior i relacions amb la UE</code>                                                          | <code>3.6700000762939453</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### projecte-aina/sts-ca
+
+* Dataset: [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca)
+* Size: 500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          | label                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                          |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 32.94 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 31.42 tokens</li><li>max: 69 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.58</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                        | sentence2                                                                                                                        | label                           |
+  |:---------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>L'euríbor puja una centèsima fins el -0,189% al gener després de setze mesos de caigudes</code>                            | <code>La morositat de bancs i caixes repunta moderadament fins el 9,44%, després d'onze mesos de caigudes</code>                 | <code>1.6699999570846558</code> |
+  | <code>Demanen 3 anys de presó a l'ex treballador d'una farmàcia de Lleida per robar més de 550 unitats de Viagra i Cialis</code> | <code>L'extreballador d'una farmàcia de Lleida accepta sis mesos de presó per robar més de 500 unitats de Viagra i Cialis</code> | <code>2.0</code>                |
+  | <code>Es tracta d'un jove de 20 anys que ha estat denunciat als Mossos d'Esquadra</code>                                         | <code>Es tracta d'un jove de 21 anys que ha estat denunciat penalment pels Mossos</code>                                         | <code>3.0</code>                |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 40
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `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`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-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`: 40
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `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`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `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`: False
+- `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
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step | Training Loss | spearman_cosine |
+|:-------:|:----:|:-------------:|:---------------:|
+| 3.8462  | 500  | 4.5209        | -               |
+| 7.6923  | 1000 | 4.1445        | -               |
+| 11.5385 | 1500 | 3.9291        | -               |
+| 15.3846 | 2000 | 3.6952        | -               |
+| 19.2308 | 2500 | 3.5393        | -               |
+| 23.0769 | 3000 | 3.3778        | -               |
+| 26.9231 | 3500 | 3.1712        | -               |
+| 30.7692 | 4000 | 2.8265        | -               |
+| 34.6154 | 4500 | 2.6265        | -               |
+| 38.4615 | 5000 | 2.3259        | -               |
+| 40.0    | 5200 | -             | 0.6820          |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.2
+- 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",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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 +1,24 @@
+{
+  "_name_or_path": "microsoft/mpnet-base",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.1",
+    "pytorch": "2.3.0+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:a59f3bb767db8f36339e5130becaa643563e96cdc95199662177a641878ce119
+size 437967672

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "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": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}