update readme

README.md

@@ -2,7 +2,7 @@
 language: fr
 license: mit
 library_name: sentence-transformers
-pipeline_tag: sentence-similarity
+pipeline_tag: feature-extraction
 tags:
     - sentence-transformers
     - feature-extraction
@@ -24,30 +24,31 @@ model-index:
           type: stsb_multi_mt
           args: fr
         metrics:
-          - name: Pearson correlation coefficient
+          - name: Pearson Correlation - stsb_multi_mt fr
             type: pearsonr
-            value: 83.7
+            value: 0.837
 ---
 
-# h4c5/sts-camembert-base
+## Description
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+Ce modèle [sentence-transformers](https://www.SBERT.net) a été obtenu en finetunant le modèle 
+[`almanach/camembert-base`](https://huggingface.co/almanach/camembert-base) à l'aide de la librairie 
+[sentence-transformers](https://www.SBERT.net).
 
-<!--- Describe your model here -->
+Il permet d'encoder une phrase ou un pararaphe (514 tokens maximum) en un vecteur de dimension 768.
 
-## Usage (Sentence-Transformers)
+Le modèle [CamemBERT](https://arxiv.org/abs/1911.03894) sur lequel il est basé est un modèle de type RoBERTa qui est 
+à l'état de l'art pour la langue française.
 
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+## Utilisation via la librairie `sentence-transformers`
 
 ```
 pip install -U sentence-transformers
 ```
 
-Then you can use the model like this:
-
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+sentences = ["Ceci est un exemple", "deuxième exemple"]
 
 model = SentenceTransformer('h4c5/sts-camembert-base')
 embeddings = model.encode(sentences)
@@ -55,50 +56,85 @@ print(embeddings)
 ```
 
 
+## Utilisation via la librairie `transformers`
 
-## Usage (HuggingFace Transformers)
-Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+```
+pip install -U transformers
+```
 
 ```python
 from transformers import AutoTokenizer, AutoModel
 import torch
 
+tokenizer = AutoTokenizer.from_pretrained("h4c5/sts-camembert-base")
+model = AutoModel.from_pretrained("h4c5/sts-camembert-base")
+model.eval()
 
-#Mean Pooling - Take attention mask into account for correct averaging
+
+# Mean Pooling
 def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+    token_embeddings = model_output[
+        0
+    ]  # First element of model_output contains all token embeddings
+    input_mask_expanded = (
+        attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    )
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(
+        input_mask_expanded.sum(1), min=1e-9
+    )
+
+# Tokenization et calcul des embeddings des tokens
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors="pt")
+model_output = model(**encoded_input)
+
+# Mean pooling
+sentence_embeddings = mean_pooling(model_output, encoded_input["attention_mask"])
 
+print(sentence_embeddings)
+```
 
-# Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
 
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('h4c5/sts-camembert-base')
-model = AutoModel.from_pretrained('h4c5/sts-camembert-base')
+## Evaluation
 
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+Le modèle a été évalué sur le jeu de données [STSb fr](https://huggingface.co/datasets/stsb_multi_mt) : 
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
+```python
+from datasets import load_dataset
+from sentence_transformers import InputExample, evaluation
 
-# Perform pooling. In this case, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
-```
+def dataset_to_input_examples(dataset):
+    return [
+        InputExample(
+            texts=[example["sentence1"], example["sentence2"]],
+            label=example["similarity_score"] / 5.0,
+        )
+        for example in dataset
+    ]
 
 
+sts_test_dataset = load_dataset("stsb_multi_mt", name="fr", split="test")
+sts_test_examples = dataset_to_input_examples(sts_test_dataset)
 
-## Evaluation Results
+sts_test_evaluator = evaluation.EmbeddingSimilarityEvaluator.from_input_examples(
+    sts_test_examples, name="sts-test"
+)
+
+sts_test_evaluator(model, ".")
+```
+
+### Résultats
 
-<!--- Describe how your model was evaluated -->
+Ci-dessous, les résultats de l'évaluation du modèle sur le jeu données [`stsb_multi_mt`](https://huggingface.co/datasets/stsb_multi_mt)
+(données `fr`, split `test`)
+
+| Model                                                                                                                                          | Pearson Correlation | Paramètres |
+| ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------- | ---------- |
+| `h4c5/sts-camembert-base`                                                                                                                      | **0.837**           | 110M       |
+| [`Lajavaness/sentence-camembert-base`](https://huggingface.co/Lajavaness/sentence-camembert-base)                                              | 0.835               | 110M       |
+| [`inokufu/flaubert-base-uncased-xnli-sts`](https://huggingface.co/inokufu/flaubert-base-uncased-xnli-sts)                                      | 0.828               | 137M       |
+| [`sentence-transformers/distiluse-base-multilingual-cased-v2`](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased) | 0.786               | 135M       |
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=h4c5/sts-camembert-base)
 
 
 ## Training
@@ -115,7 +151,7 @@ The model was trained with the parameters:
 
 `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
 
-Parameters of the fit()-Method:
+Parameters of the `fit()` method:
 ```
 {
     "epochs": 10,
@@ -135,6 +171,7 @@ Parameters of the fit()-Method:
 
 
 ## Full Model Architecture
+
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: CamembertModel 
@@ -144,16 +181,18 @@ SentenceTransformer(
 
 ## Citing
 
-@article{reimers2019sentence,
-   title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
-   author={Nils Reimers, Iryna Gurevych},
-   journal={https://arxiv.org/abs/1908.10084},
-   year={2019}
-}
-
-@inproceedings{martin2020camembert,
-  title={CamemBERT: a Tasty French Language Model},
-  author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t},
-  booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
-  year={2020}
-}
+    @article{reimers2019sentence,
+       title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
+       author={Nils Reimers, Iryna Gurevych},
+       journal={https://arxiv.org/abs/1908.10084},
+       year={2019}
+    }
+
+
+    @inproceedings{martin2020camembert,
+      title={CamemBERT: a Tasty French Language Model},
+      author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t},
+      booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
+      journal={https://arxiv.org/abs/1911.03894},
+      year={2020}
+    }