gabrielmotablima commited on
Commit
f246702
1 Parent(s): 9d388f2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -54,7 +54,7 @@ The encoder checkpoints come from Swin Trasnformer version pre-trained on ImageN
54
  The code used for training and evaluation is available at: https://github.com/laicsiifes/ved-transformer-caption-ptbr. In this work, Swin-GPorTuguese-2
55
  was trained together with its buddy [Swin-DistilBERTimbau](https://huggingface.co/laicsiifes/swin-distilbert-flickr30k-pt-br).
56
 
57
- Other models evaluated didn't achieve performance as high as Swin-DistilBERTimbau and Swin-GPorTuguese-2, namely: DeiT-BERTimbau,
58
  DeiT-DistilBERTimbau, DeiT-GPorTuguese-2, Swin-BERTimbau, ViT-BERTimbau, ViT-DistilBERTimbau and ViT-GPorTuguese-2.
59
 
60
  ## 🧑‍💻 How to Get Started with the Model
 
54
  The code used for training and evaluation is available at: https://github.com/laicsiifes/ved-transformer-caption-ptbr. In this work, Swin-GPorTuguese-2
55
  was trained together with its buddy [Swin-DistilBERTimbau](https://huggingface.co/laicsiifes/swin-distilbert-flickr30k-pt-br).
56
 
57
+ Other models evaluated did not perform as well as Swin-DistilBERTimbau and Swin-GPorTuguese-2, namely: DeiT-BERTimbau,
58
  DeiT-DistilBERTimbau, DeiT-GPorTuguese-2, Swin-BERTimbau, ViT-BERTimbau, ViT-DistilBERTimbau and ViT-GPorTuguese-2.
59
 
60
  ## 🧑‍💻 How to Get Started with the Model