fix readme.md

README.md

@@ -25,7 +25,8 @@ tags:
 
 Paper: [DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193)](https://arxiv.org/abs/2304.07193) · [HF Papers](https://huggingface.co/papers/2304.07193)
 
-DINOv2 scales self-supervised ViT pretraining for strong transferable visual features without labels. These checkpoints are backbones that return patch tokens for downstream heads.\n
+DINOv2 scales self-supervised ViT pretraining for strong transferable visual features without labels. These checkpoints are backbones that return patch tokens for downstream heads.
+
 For more details on the model, please go to the upstream [model card](https://huggingface.co/facebook/dinov2-base).
 
 Pure-**Keras 3** conversion of [`facebook/dinov2-base`](https://huggingface.co/facebook/dinov2-base) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
@@ -40,9 +41,9 @@ os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
 import numpy as np
 from PIL import Image
-from {meta['import_path']} import {meta['load_cls']}
+from kerasformers.models.dino_v2 import DinoV2Model
 
-model = {meta["load_cls"]}.from_weights("kerasformers/{variant}", image_size=448)
+model = DinoV2Model.from_weights("kerasformers/dinov2_vitb14", image_size=448)
 image = Image.open("your_image.jpg").convert("RGB")
 x = np.asarray(image.resize((448, 448)))[None].astype("float32")
 tokens = model(x, training=False)