Update README.md

README.md

@@ -13,19 +13,19 @@ widget:
 DistilCamemBERT-Sentiment
 =========================
 
-We present DistilCamemBERT-Sentiment which is [DistilCamemBERT](https://huggingface.co/cmarkea/distilcamembert-base) fine tuned for the sentiment analysis task for the French language. This model is constructed over 2 datasets: [Amazon Reviews](https://huggingface.co/datasets/amazon_reviews_multi) and [Allociné.fr](https://huggingface.co/datasets/allocine) in order to minimize the bias. Indeed, Amazon reviews are very similar in the messages and relatively shorts, contrary to Allociné critics which are long and rich texts.
+We present DistilCamemBERT-Sentiment, which is [DistilCamemBERT](https://huggingface.co/cmarkea/distilcamembert-base) fine-tuned for the sentiment analysis task for the French language. This model is built using two datasets: [Amazon Reviews](https://huggingface.co/datasets/amazon_reviews_multi) and [Allociné.fr](https://huggingface.co/datasets/allocine) to minimize the bias. Indeed, Amazon reviews are similar in messages and relatively shorts, contrary to Allociné critics, who are long and rich texts.
 
-This modelization is close to [tblard/tf-allocine](https://huggingface.co/tblard/tf-allocine) based on [CamemBERT](https://huggingface.co/camembert-base) model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by 2** with the same consumption power thanks to [DistilCamemBERT](https://huggingface.co/cmarkea/distilcamembert-base).
+This modelization is close to [tblard/tf-allocine](https://huggingface.co/tblard/tf-allocine) based on [CamemBERT](https://huggingface.co/camembert-base) model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to [DistilCamemBERT](https://huggingface.co/cmarkea/distilcamembert-base).
 
 Dataset
 -------
 
-The dataset is composed of 204,993 reviews for training and 4,999 reviews for the test coming from Amazon, and respectively 235,516 and 4,729 critics from [Allocine website](https://www.allocine.fr/). The dataset is labeled into 5 categories:
-* 1 star: represents a very bad appreciation,
+The dataset comprises 204,993 reviews for training and 4,999 reviews for the test from Amazon, and 235,516 and 4,729 critics from [Allocine website](https://www.allocine.fr/). The dataset is labeled into five categories:
+* 1 star: represents a terrible appreciation,
 * 2 stars: bad appreciation,
 * 3 stars: neutral appreciation,
 * 4 stars: good appreciation,
-* 5 stars: very good appreciation. 
+* 5 stars: excellent appreciation. 
  
 Evaluation results
 ------------------
@@ -48,10 +48,10 @@ where \\(\hat{f}_l\\) is the l-th largest predicted label, \\(y\\) the true labe
 Benchmark
 ---------
 
-This model is compared to 3 reference models (see below). As each model doesn't have the same definition of targets, we detail the performance measure used for each of them. For the mean inference time measure, an **AMD Ryzen 5 4500U @ 2.3GHz with 6 cores** was used.
+This model is compared to 3 reference models (see below). As each model doesn't have the exact definition of targets, we detail the performance measure used for each. An **AMD Ryzen 5 4500U @ 2.3GHz with 6 cores** was used for the mean inference time measure.
 
 #### bert-base-multilingual-uncased-sentiment
-[nlptown/bert-base-multilingual-uncased-sentiment](https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment) is based on BERT model in the multilingual and uncased version. This sentiment analyzer is trained on Amazon reviews similarly to our model, hence the targets and their definitions are the same.
+[nlptown/bert-base-multilingual-uncased-sentiment](https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment) is based on BERT model in the multilingual and uncased version. This sentiment analyzer is trained on Amazon reviews, similar to our model. Hence the targets and their definitions are the same.
 
 | **model** | **time (ms)** | **exact accuracy (%)** | **top-2 acc (%)** |
 | :-------: | :-----------: | :--------------------: | :---------------: |
@@ -96,6 +96,24 @@ result
   'score': 0.13417290151119232}]
 ```
 
+### Optimum + ONNX
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer, pipeline
+
+HUB_MODEL = "cmarkea/distilcamembert-base-nli"
+
+tokenizer = AutoTokenizer.from_pretrained(HUB_MODEL)
+model = ORTModelForSequenceClassification.from_pretrained(HUB_MODEL)
+onnx_qa = pipeline("text-classification", model=model, tokenizer=tokenizer)
+
+# Quantized onnx model
+quantized_model = ORTModelForSequenceClassification.from_pretrained(
+    HUB_MODEL, file_name="model_quantized.onnx"
+)
+```
+
 Citation
 --------
 ```bibtex