Update README.md

README.md

@@ -5,6 +5,7 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
+- fr
 ---
 
 # hugorosen/flaubert_base_uncased-xnli-sts
@@ -25,7 +26,7 @@ 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 une phrase d'exemple", "Chaque phrase est convertie"]
 
 model = SentenceTransformer('hugorosen/flaubert_base_uncased-xnli-sts')
 embeddings = model.encode(sentences)
@@ -50,7 +51,7 @@ def mean_pooling(model_output, attention_mask):
 
 
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+sentences = ["Ceci est une phrase d'exemple", "Chaque phrase est convertie"]
 
 # Load model from HuggingFace Hub
 tokenizer = AutoTokenizer.from_pretrained('hugorosen/flaubert_base_uncased-xnli-sts')
@@ -76,22 +77,17 @@ print(sentence_embeddings)
 
 <!--- Describe how your model was evaluated -->
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=hugorosen/flaubert_base_uncased-xnli-sts)
+This model scores 76.9% on STS test (french)
 
 
 ## Training
-The model was trained with the parameters:
+### Pre-training
 
-**DataLoader**:
+We use the pre-trained [flaubert/flaubert_base_uncased](https://huggingface.co/flaubert/flaubert_base_cased). Please refer to the model card for more detailed information about the pre-training procedure.
 
-`torch.utils.data.dataloader.DataLoader` of length 360 with parameters:
-```
-{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
-```
-
-**Loss**:
+### Fine-tuning
 
-`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+we fine-tune the model using a `CosineSimilarityLoss` on XNLI and STS dataset (french).
 
 Parameters of the fit()-Method:
 ```