Update README.md

README.md

@@ -22,8 +22,23 @@ By removing the decoder we can *half the original number of parameters* (thus ha
 
 ## Table of Contents
 
-0. [Why use T5ForSequenceClassification?](##why-use-t5forsequenceclassification?)
-1. [T5ForClassification vs T5](##t5forclassification-vs-t5)
+0. [Usage](##usage)
+1. [Why use T5ForSequenceClassification?](##why-use-t5forsequenceclassification?)
+2. [T5ForClassification vs T5](##t5forclassification-vs-t5)
+
+## Usage
+**T5ForSequenceClassification** supports the task of zero-shot classification.
+It can direclty be used for:
+- topic classification
+- intent recognition
+- boolean question answering
+- sentiment analysis
+- and any other task which goal is to clasify a text...
+
+Since the *T5ForClassification* class is currently not supported by the transformers library, you cannot direclty use this model on the Hub.
+To use **T5ForSequenceClassification**, you will have to install additional packages and model weights.
+You can find instructions [here](https://github.com/AntoineBlanot/zero-nlp).
+
 
 ## Why use T5ForSequenceClassification?
 Models based on the [BERT](https://huggingface.co/bert-large-uncased) architecture like [RoBERTa](https://huggingface.co/roberta-large) and [DeBERTa](https://huggingface.co/microsoft/deberta-v2-xxlarge) have shown very strong performance on sequence classification task and are still widely used today.