AntoineBlanot commited on
Commit
d2fe8b6
1 Parent(s): 360ec4b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -22,8 +22,8 @@ By removing the decoder we can *half the original number of parameters* (thus ha
22
 
23
  ## Table of Contents
24
 
25
- 1. [Why use T5ForSequenceClassification?](##why-use-t5forsequenceclassification?)
26
- 2. [T5ForClassification vs T5](##t5forclassification-vs-t5)
27
 
28
  ## Why use T5ForSequenceClassification?
29
  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.
 
22
 
23
  ## Table of Contents
24
 
25
+ 0. [Why use T5ForSequenceClassification?](##why-use-t5forsequenceclassification?)
26
+ 1. [T5ForClassification vs T5](##t5forclassification-vs-t5)
27
 
28
  ## Why use T5ForSequenceClassification?
29
  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.