Update README.md

README.md

@@ -7,6 +7,11 @@ license: apache-2.0
 ---
 # Model card for kat_tiny_patch16_224
 
+KAT model trained on ImageNet-1k (1 million images, 1,000 classes) at resolution 224x224. It was first introduced in the paper Kolmogorov–Arnold Transformer.
+
+## Model description
+KAT is a model that replaces channel mixer in transfomrers with Group Rational Kolmogorov–Arnold Network~(GR-KAN).
+
 ## Usage
 
 ```python
@@ -40,3 +45,15 @@ print(top5_probabilities)
 print(top5_class_indices)
 
 ```
+
+## Bibtex
+```bibtex
+@misc{yang2024compositional,
+    title={Kolmogorov–Arnold Transformer},
+    author={Xingyi Yang and Xinchao Wang},
+    year={2024},
+    eprint={XXXX},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```