Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,26 @@ tags:
|
|
7 |
repo_url: https://github.com/facebookresearch/jepa
|
8 |
---
|
9 |
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
repo_url: https://github.com/facebookresearch/jepa
|
8 |
---
|
9 |
|
10 |
+
## V-JEPA model
|
11 |
+
|
12 |
+
This is a Vision Transformer (ViT) large model, trained using the V-JEPA method.
|
13 |
+
|
14 |
+
## Installation
|
15 |
+
|
16 |
+
First, clone and install the [JEPA package](https://github.com/facebookresearch/jepa/tree/main):
|
17 |
+
|
18 |
+
```bash
|
19 |
+
!git clone -b add_hf https://github.com/nielsrogge/jepa.git
|
20 |
+
!cd jepa
|
21 |
+
!pip install -r requirements.txt
|
22 |
+
```
|
23 |
+
|
24 |
+
## Usage
|
25 |
+
|
26 |
+
One can instantiate the model as follows:
|
27 |
+
|
28 |
+
```python
|
29 |
+
from src.models.vision_transformer import VisionTransformer
|
30 |
+
|
31 |
+
model = VisionTransformer.from_pretrained("nielsr/vit-large-patch16-v-jepa")
|
32 |
+
```
|