gabrielmotablima commited on
Commit
4ca27c2
1 Parent(s): 83a35d1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ at resolution 224x224 and max sequence length of 1024 tokens.
23
  ## 🤖 Model Description
24
 
25
  The Swin-GPorTuguese-2 is a type of Vision Encoder Decoder which leverage the checkpoints of the [Swin Transformer](https://huggingface.co/microsoft/swin-base-patch4-window7-224)
26
- as encoder and the checkpoints of the [GPorTuguese-2](pierreguillou/gpt2-small-portuguese) as decoder.
27
  The encoder checkpoints come from Swin Trasnformer version pre-trained on ImageNet-1k at resolution 224x224.
28
 
29
  The code used for training and evaluation is available at: https://github.com/laicsiifes/ved-transformer-caption-ptbr. In this work, Swin-GPorTuguese-2
 
23
  ## 🤖 Model Description
24
 
25
  The Swin-GPorTuguese-2 is a type of Vision Encoder Decoder which leverage the checkpoints of the [Swin Transformer](https://huggingface.co/microsoft/swin-base-patch4-window7-224)
26
+ as encoder and the checkpoints of the [GPorTuguese-2](https://huggingface.co/pierreguillou/gpt2-small-portuguese) as decoder.
27
  The encoder checkpoints come from Swin Trasnformer version pre-trained on ImageNet-1k at resolution 224x224.
28
 
29
  The code used for training and evaluation is available at: https://github.com/laicsiifes/ved-transformer-caption-ptbr. In this work, Swin-GPorTuguese-2