Update README.md

README.md

@@ -13,11 +13,19 @@ The key idea is to combine the bounding box modality with text, achieving a pixe
 
 ![Example Image](https://raw.githubusercontent.com/veya2ztn/Lougat/main/images/image.png)
 
-The name "Lougat" is a combination of LLama and Nougat. In this repo, you'll also find other combinations like:
+The name "Lougat" is a combination of LLama and Nougat. The key idea is nature continues of this paper [LOCR: Location-Guided Transformer for Optical Character Recognition]([[2403.02127\] LOCR: Location-Guided Transformer for Optical Character Recognition (arxiv.org)](https://arxiv.org/abs/2403.02127))
 
+Current Branch: The **LOCR** model
+
+Other Branch:
 - Florence2 + LLama → Flougat
 - Sam2 + LLama → Slougat
 - Nougat + Relative Position Embedding LLama → Rlougat
 
-The key idea is nature continues of this paper [LOCR: Location-Guided Transformer for Optical Character Recognition]([[2403.02127\] LOCR: Location-Guided Transformer for Optical Character Recognition (arxiv.org)](https://arxiv.org/abs/2403.02127))
+
+# Inference and Train
+
+Please see `https://github.com/veya2ztn/Lougat`
+
+