Link model to paper (#1)
Browse files- Link model to paper (79041b77cf17de31e2aee9be8a61ff4cee62b0fe)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
|
@@ -7,7 +7,7 @@ license: apache-2.0
|
|
| 7 |
---
|
| 8 |
# Model card for kat_tiny_patch16_224
|
| 9 |
|
| 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).
|
|
|
|
| 7 |
---
|
| 8 |
# Model card for kat_tiny_patch16_224
|
| 9 |
|
| 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](https://huggingface.co/papers/2409.10594).
|
| 11 |
|
| 12 |
## Model description
|
| 13 |
KAT is a model that replaces channel mixer in transfomrers with Group Rational Kolmogorov–Arnold Network (GR-KAN).
|