Update README.md

README.md

@@ -20,9 +20,23 @@ You can find [here](https://huggingface.co/google/flan-t5-base?text=Premise%3A++
 Our motivations for building **T5ForSequenceClassification** is that the full original T5 architecture is not needed for most NLU tasks. Indeed, NLU tasks generally do not require to generate text and thus a large decoder is unnecessary.
 By removing the decoder we can *half the original number of parameters* (thus half the computation cost) and *efficiently optimize* the network for the given task.
 
-# Why use T5ForSequenceClassification?
+## 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.
 However, those models only scale up to ~1.5B parameters (DeBERTa xxlarge) resulting in a limited knowledge compare to bigger models.
-On the other hand, models based on the T5 architecture scale up to ~11B parameters (t5-xxl) and innovations with this architecture are very recent and keeps improving (T5, [mT5](https://huggingface.co/google/mt5-xxl), [Flan-T5](https://huggingface.co/google/flan-t5-xxl), [UL2](https://huggingface.co/google/ul2), [Flan-UL2](https://huggingface.co/google/flan-ul2), and probably more...) 
+On the other hand, models based on the T5 architecture scale up to ~11B parameters (t5-xxl) and innovations with this architecture are very recent and keeps improving ([mT5](https://huggingface.co/google/mt5-xxl), [Flan-T5](https://huggingface.co/google/flan-t5-xxl), [UL2](https://huggingface.co/google/ul2), [Flan-UL2](https://huggingface.co/google/flan-ul2), and probably more...) 
 
-Model of philschmid/flan-t5-xxl-sharded-fp16 with a single decoder layer and a classification head on top.
+## T5ForClassification vs T5
+**T5ForClassification** Architecture:
+- Encoder: same as original T5
+- Decoder: only the first layer (for pooling purpose)
+- Classification head: simple Linear layer on top of the decoder
+
+Benefits and Drawbacks:
+- (**+**) Keeps T5 encoding strength
+- (**+**) Parameters size is half
+- (**+**) Interpretable outputs (class logits)
+- (**+**) No generation mistakes and faster prediction (no generation latency)
+- (**-**) Looses text-to-text ability
+
+
+Special thanks to [philschmid](https://huggingface.co/philschmid) for making a Flan-T5-xxl [checkpoint](https://huggingface.co/philschmid/flan-t5-xxl-sharded-fp16) in fp16.