Update docs/source/en/training/cogvideox.md

Co-authored-by: Steven Liu <[email protected]>

Author: glide-the

docs/source/en/training/cogvideox.md

@@ -72,7 +72,7 @@ You could use a single CSV file. For the sake of this example, assume you have a
 ...
 ```
 
-In this case, the `--instance_data_root` should be the location where the videos are stored and `--dataset_name` should be either a path to local folder or `load_dataset` compatible hosted HF Dataset Repository or URL. Assuming you have videos of your Minecraft gameplay at `https://huggingface.co/datasets/my-awesome-username/minecraft-videos`, you would have to specify `my-awesome-username/minecraft-videos`.
+In this case, the `--instance_data_root` should be the location where the videos are stored and `--dataset_name` should be either a path to local folder or a [`~datasets.load_dataset`] compatible dataset hosted on the Hub. Assuming you have videos of Minecraft gameplay at `https://huggingface.co/datasets/my-awesome-username/minecraft-videos`, you would have to specify `my-awesome-username/minecraft-videos`.
 
 When using this format, the `--caption_column` must be `<CAPTION_COLUMN>` and `--video_column` must be `<PATH_TO_VIDEO_COLUMN>`.