Upload README.md with huggingface_hub

README.md

@@ -1,76 +1,81 @@
 ---
-license: apache-2.0
-library_name: mlx-image
-tags:
-- mlx
-- mlx-image
-- vision
-- image-classification
-datasets:
-- imagenet-1k
+{}
 ---
-# vit_small_patch14_518.dinov2
 
-A [Vision Transformer](https://arxiv.org/abs/2010.11929v2) image classification model trained on ImageNet-1k dataset with [DINOv2](https://arxiv.org/abs/2304.07193).
+    ---
+    license: apache-2.0
+    tags:
+    - mlx
+    - mlx-image
+    - vision
+    - image-classification
+    datasets:
+    - imagenet-1k
+    library_name: mlx-image
+    ---
+    # vit_small_patch14_518.dinov2
 
-The model was trained in self-supervised fashion on ImageNet-1k dataset. No classification head was trained, only the backbone.
+    A [Vision Transformer](https://arxiv.org/abs/2010.11929v2) image classification model trained on ImageNet-1k dataset with [DINOv2](https://arxiv.org/abs/2304.07193).
 
-Disclaimer: This is a porting of the torch model weights to Apple MLX Framework.
+    The model was trained in self-supervised fashion on ImageNet-1k dataset. No classification head was trained, only the backbone.
 
-<div align="center">
-  <img width="100%" alt="DINO illustration" src="dino.gif">
-</div>
+    Disclaimer: This is a porting of the torch model weights to Apple MLX Framework.
 
+    <div align="center">
+    <img width="100%" alt="DINO illustration" src="dino.gif">
+    </div>
 
-## How to use
-```bash
-pip install mlx-image
-```
 
-Here is how to use this model for image classification:
+    ## How to use
+    ```bash
+    pip install mlx-image
+    ```
 
-```python
-from mlxim.model import create_model
-from mlxim.io import read_rgb
-from mlxim.transform import ImageNetTransform
+    Here is how to use this model for image classification:
 
-transform = ImageNetTransform(train=False, img_size=518)
-x = transform(read_rgb("cat.png"))
-x = mx.expand_dims(x, 0)
+    ```python
+    from mlxim.model import create_model
+    from mlxim.io import read_rgb
+    from mlxim.transform import ImageNetTransform
 
-model = create_model("vit_small_patch14_518.dinov2")
-model.eval()
+    transform = ImageNetTransform(train=False, img_size=518)
+    x = transform(read_rgb("cat.png"))
+    x = mx.expand_dims(x, 0)
 
-logits, attn_masks = model(x, attn_masks=True)
-```
+    model = create_model("vit_small_patch14_518.dinov2")
+    model.eval()
 
-You can also use the embeds from layer before head:
-```python
-from mlxim.model import create_model
-from mlxim.io import read_rgb
-from mlxim.transform import ImageNetTransform
+    logits, attn_masks = model(x, attn_masks=True)
+    ```
 
-transform = ImageNetTransform(train=False, img_size=512)
-x = transform(read_rgb("cat.png"))
-x = mx.expand_dims(x, 0)
+    You can also use the embeds from layer before head:
+    ```python
+    from mlxim.model import create_model
+    from mlxim.io import read_rgb
+    from mlxim.transform import ImageNetTransform
 
-# first option
-model = create_model("vit_small_patch14_518.dinov2", num_classes=0)
-model.eval()
+    transform = ImageNetTransform(train=False, img_size=512)
+    x = transform(read_rgb("cat.png"))
+    x = mx.expand_dims(x, 0)
 
-embeds = model(x)
+    # first option
+    model = create_model("vit_small_patch14_518.dinov2", num_classes=0)
+    model.eval()
 
-# second option
-model = create_model("vit_small_patch14_518.dinov2")
-model.eval()
+    embeds = model(x)
 
-embeds, attn_masks = model.get_features(x)
-```
+    # second option
+    model = create_model("vit_small_patch14_518.dinov2")
+    model.eval()
 
-## Attention maps
-You can visualize the attention maps using the `attn_masks` returned by the model. Go check the mlx-image [notebook](https://github.com/riccardomusmeci/mlx-image/notebooks/dino_attention.ipynb).
+    embeds, attn_masks = model.get_features(x)
+    ```
 
-<div align="center">
-  <img width="100%" alt="Attention Map" src="attention_maps.png">
-</div>
+    ## Attention maps
+    You can visualize the attention maps using the `attn_masks` returned by the model. Go check the mlx-image [notebook](https://github.com/riccardomusmeci/mlx-image/blob/main/notebooks/dino_attention.ipynb).
 
+    <div align="center">
+    <img width="100%" alt="Attention Map" src="attention_maps.png">
+    </div>
+
+