Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ license: apache-2.0
|
|
10 |
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.
|
11 |
|
12 |
## Model description
|
13 |
-
KAT is a model that replaces channel mixer in transfomrers with Group Rational Kolmogorov–Arnold Network
|
14 |
|
15 |
## Usage
|
16 |
|
|
|
10 |
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.
|
11 |
|
12 |
## Model description
|
13 |
+
KAT is a model that replaces channel mixer in transfomrers with Group Rational Kolmogorov–Arnold Network (GR-KAN).
|
14 |
|
15 |
## Usage
|
16 |
|