Update README.md

README.md

@@ -4,7 +4,14 @@ license: mit
 
 # ERNIE-Layout_Pytorch
 
-[This repository](https://github.com/NormXU/ERNIE-Layout-Pytorch) contains an unofficial ERNIE-Layout implementations in Pytorch, originally released via [PaddleNLP](https://github.com/PaddlePaddle/PaddleNLP). The model weight is converted from [PaddlePaddle/ernie-layoutx-base-uncased](https://huggingface.co/PaddlePaddle/ernie-layoutx-base-uncased) to PyTorch style with the [tools/convert2torch.py](https://github.com/NormXU/ERNIE-Layout-Pytorch/blob/main/tools/convert2torch.py) script. Feel free to edit it if necessary.
+- **Model type:** [ERNIE-Layout](https://arxiv.org/abs/2210.06155)
+- **Repository:** [source code](https://github.com/NormXU/ERNIE-Layout-Pytorch): an unofficial ERNIE-Layout implementation in Pytorch
+  
+- **Converted from:** [PaddlePaddle/ernie-layoutx-base-uncased](https://huggingface.co/PaddlePaddle/ernie-layoutx-base-uncased)
+  
+
+The ERNIE-Layout-Pytorch model is initially released by [PaddleNLP](https://github.com/PaddlePaddle/PaddleNLP). To make Pytorch users easy to use, the model has been converted into PyTorch format with the [tools/convert2torch.py](https://github.com/NormXU/ERNIE-Layout-Pytorch/blob/main/tools/convert2torch.py) script.
+Please feel free to make any changes you need. For more details and use cases, please check the repo.
 
 **A Quick Example**
 ```python
@@ -56,5 +63,4 @@ answer = tokenizer.decode(encoding.input_ids[0][start_max: end_max])
 print(answer)
 
 
-
 ```