fix 404

README.md

@@ -31,7 +31,7 @@ We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignme
 
 ## Dataset
 
-This model was fine-tuned from [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on the [Pick-Safety](mapo-t2i/pick-safety). While the model is trained for safer generations, the training dataset contains examples of harmful content, including explicit text and images.
+This model was fine-tuned from [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on the [Pick-Safety](https://huggingface.co/datasets/mapo-t2i/pick-safety). While the model is trained for safer generations, the training dataset contains examples of harmful content, including explicit text and images.
 
 ## Training Code