Update README.md

README.md

@@ -19,7 +19,7 @@ Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a sta
 
 We release three pre-trained models:
 
-| Model                | Zero-shot Accuracy (ImageNet-1K) | Link |
+| Model | Zero-shot Accuracy (ImageNet-1K) | Link |
 |----|----|----|
 | UTA-B | 77.0% | [weights](https://huggingface.co/jjjjh/UTA/tree/main/checkpoints) |
 | UTA-L-pix336 | 81.4% | [weights](https://huggingface.co/jjjjh/UTA/tree/main/checkpoints) |
@@ -29,7 +29,7 @@ We release three pre-trained models:
 
 1. **Clone this repository:**
    ```bash
-   git clone https://github.com/jihaonew/UTA.git
+   git clone https://huggingface.co/jjjjh/UTA
    cd UTA
    ```