Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,14 @@ The code is released [in this repository](https://github.com/facebookresearch/vj
|
|
| 12 |
|
| 13 |
<img src="https://dl.fbaipublicfiles.com/vjepa2/vjepa2-pretrain.gif">
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Intended Uses
|
| 16 |
|
| 17 |
V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs.
|
|
|
|
| 12 |
|
| 13 |
<img src="https://dl.fbaipublicfiles.com/vjepa2/vjepa2-pretrain.gif">
|
| 14 |
|
| 15 |
+
## Installation
|
| 16 |
+
|
| 17 |
+
To run V-JEPA 2 model, ensure you have installed the latest transformers:
|
| 18 |
+
|
| 19 |
+
```bash
|
| 20 |
+
pip install -U git+https://github.com/huggingface/transformers
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
## Intended Uses
|
| 24 |
|
| 25 |
V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs.
|