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 +1,581 @@
+---
+language:
+- de
+- en
+- es
+- fr
+- it
+- nl
+- pl
+- pt
+- ru
+- zh
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:5749
+- loss:CoSENTLoss
+base_model: ymelka/camembert-cosmetic-finetuned
+datasets:
+- PhilipMay/stsb_multi_mt
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Nous nous déplaçons "... par rapport au cadre de repos cosmique
+    en mouvement ... à environ 371 km/s vers la constellation du Lion".
+  sentences:
+  - La dame a fait frire la viande panée dans de l'huile chaude.
+  - Il n'y a pas d'alambic qui ne soit pas relatif à un autre objet.
+  - Le joueur de basket-ball est sur le point de marquer des points pour son équipe.
+- source_sentence: Le professeur Burkhauser a effectué des recherches approfondies
+    sur les personnes qui sont pénalisées par l'augmentation du salaire minimum.
+  sentences:
+  - Un adolescent parle à une fille par le biais d'une webcam.
+  - Une femme est en train de couper des oignons verts.
+  - Les lois sur le salaire minimum nuisent le plus aux personnes les moins qualifiées
+    et les moins productives.
+- source_sentence: Bien que le terme "reine" puisse faire référence à la fois à la
+    reine régente (souveraine) ou à la reine consort, le roi a toujours été le souverain.
+  sentences:
+  - Des moutons paissent dans le champ devant une rangée d'arbres.
+  - Il y a une très bonne raison de ne pas appeler le conjoint de la Reine "Roi" -
+    parce qu'il n'est pas le Roi.
+  - Un groupe de personnes âgées pose autour d'une table à manger.
+- source_sentence: Deux pygargues à tête blanche perchés sur une branche.
+  sentences:
+  - Un groupe de militaires joue dans un quintette de cuivres.
+  - Deux aigles sont perchés sur une branche.
+  - Un homme qui joue de la guitare sous la pluie.
+- source_sentence: Un homme joue de la guitare.
+  sentences:
+  - Il est possible qu'un système solaire comme le nôtre existe en dehors d'une galaxie.
+  - Un homme joue de la flûte.
+  - Un homme est en train de manger une banane.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on ymelka/camembert-cosmetic-finetuned
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb fr dev
+      type: stsb-fr-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.6401461834329478
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6661576168424006
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7077411059971963
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7104395816607704
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6183470655093759
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6339424060254548
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.18614455072383299
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.21677402345623561
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7077411059971963
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.7104395816607704
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.834390325106948
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8564941342147334
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8518548236293758
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.854193303324745
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8541012365072966
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8555434573522197
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4989804086580052
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5094008186566353
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8541012365072966
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8564941342147334
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb fr test
+      type: stsb-fr-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.7979696368103
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8219240068315988
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8237827107867745
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8221440625680553
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8230384709547542
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8218369251066925
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4089365107737232
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.4588995887587045
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8237827107867745
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8221440625680553
+      name: Spearman Max
+---
+
+# SentenceTransformer based on ymelka/camembert-cosmetic-finetuned
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [ymelka/camembert-cosmetic-finetuned](https://huggingface.co/ymelka/camembert-cosmetic-finetuned) on the [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) 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:** [ymelka/camembert-cosmetic-finetuned](https://huggingface.co/ymelka/camembert-cosmetic-finetuned) <!-- at revision cd4cb90f9388340c5f02740130efd30336c08905 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+- **Languages:** de, en, es, fr, it, nl, pl, pt, ru, zh
+<!-- - **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': 512, 'do_lower_case': False}) with Transformer model: CamembertModel 
+  (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("ymelka/camembert-cosmetic-similarity")
+# Run inference
+sentences = [
+    'Un homme joue de la guitare.',
+    'Un homme est en train de manger une banane.',
+    'Un homme joue de la flûte.',
+]
+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
+* Dataset: `stsb-fr-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6401     |
+| **spearman_cosine** | **0.6662** |
+| pearson_manhattan   | 0.7077     |
+| spearman_manhattan  | 0.7104     |
+| pearson_euclidean   | 0.6183     |
+| spearman_euclidean  | 0.6339     |
+| pearson_dot         | 0.1861     |
+| spearman_dot        | 0.2168     |
+| pearson_max         | 0.7077     |
+| spearman_max        | 0.7104     |
+
+#### Semantic Similarity
+* Dataset: `stsb-fr-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8344     |
+| **spearman_cosine** | **0.8565** |
+| pearson_manhattan   | 0.8519     |
+| spearman_manhattan  | 0.8542     |
+| pearson_euclidean   | 0.8541     |
+| spearman_euclidean  | 0.8555     |
+| pearson_dot         | 0.499      |
+| spearman_dot        | 0.5094     |
+| pearson_max         | 0.8541     |
+| spearman_max        | 0.8565     |
+
+#### Semantic Similarity
+* Dataset: `stsb-fr-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.798      |
+| **spearman_cosine** | **0.8219** |
+| pearson_manhattan   | 0.8238     |
+| spearman_manhattan  | 0.8221     |
+| pearson_euclidean   | 0.823      |
+| spearman_euclidean  | 0.8218     |
+| pearson_dot         | 0.4089     |
+| spearman_dot        | 0.4589     |
+| pearson_max         | 0.8238     |
+| spearman_max        | 0.8221     |
+
+<!--
+## 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
+
+#### PhilipMay/stsb_multi_mt
+
+* Dataset: [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | score                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | float                                                         |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 11.1 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 11.04 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.7</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                  | sentence2                                                            | score                          |
+  |:-----------------------------------------------------------|:---------------------------------------------------------------------|:-------------------------------|
+  | <code>Un avion est en train de décoller.</code>            | <code>Un avion est en train de décoller.</code>                      | <code>5.0</code>               |
+  | <code>Un homme joue d'une grande flûte.</code>             | <code>Un homme joue de la flûte.</code>                              | <code>3.799999952316284</code> |
+  | <code>Un homme étale du fromage râpé sur une pizza.</code> | <code>Un homme étale du fromage râpé sur une pizza non cuite.</code> | <code>3.799999952316284</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
+
+#### PhilipMay/stsb_multi_mt
+
+* Dataset: [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 17.45 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 17.35 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.36</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                                | sentence2                                                                   | score             |
+  |:-------------------------------------------------------------------------|:----------------------------------------------------------------------------|:------------------|
+  | <code>Un homme avec un casque de sécurité est en train de danser.</code> | <code>Un homme portant un casque de sécurité est en train de danser.</code> | <code>5.0</code>  |
+  | <code>Un jeune enfant monte à cheval.</code>                             | <code>Un enfant monte à cheval.</code>                                      | <code>4.75</code> |
+  | <code>Un homme donne une souris à un serpent.</code>                     | <code>L'homme donne une souris au serpent.</code>                           | <code>5.0</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
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.01
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `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`: 2e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3
+- `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`: True
+- `fp16`: False
+- `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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | stsb-fr-dev_spearman_cosine | stsb-fr-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:---------------------------:|:----------------------------:|
+| 0      | 0    | -             | -      | 0.6661                      | -                            |
+| 0.2778 | 100  | 4.9452        | 4.4417 | 0.7733                      | -                            |
+| 0.5556 | 200  | 4.667         | 4.4273 | 0.7986                      | -                            |
+| 0.8333 | 300  | 4.4904        | 4.3058 | 0.8338                      | -                            |
+| 1.1111 | 400  | 4.1679        | 4.2723 | 0.8491                      | -                            |
+| 1.3889 | 500  | 4.138         | 4.3575 | 0.8464                      | -                            |
+| 1.6667 | 600  | 4.5737        | 4.3427 | 0.8479                      | -                            |
+| 1.9444 | 700  | 4.3086        | 4.4455 | 0.8510                      | -                            |
+| 2.2222 | 800  | 3.8711        | 4.4135 | 0.8590                      | -                            |
+| 2.5    | 900  | 4.064         | 4.4775 | 0.8567                      | -                            |
+| 2.7778 | 1000 | 4.2255        | 4.4733 | 0.8565                      | -                            |
+| 3.0    | 1080 | -             | -      | -                           | 0.8219                       |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.31.0
+- 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>NOTUSED": 32005
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "ymelka/camembert-cosmetic-finetuned",
+  "architectures": [
+    "CamembertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "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": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "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 sha256:6f66d6be5bb6bba34ea50403bf4983ee4721b9b78dc9793bb7a0081fff3173f0
+size 442510176

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
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,56 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "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_config.json

@@ -0,0 +1,90 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "CamembertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}