Update README.md

README.md

@@ -122,7 +122,7 @@ The model can work fully zero-shot or use available ground-truth for maximum acc
 - Individual attributes for each character for recognition on images with multiple characters (both popular tags and regular descriptions are supported)
 - Separate booru tags or brief descriptions of what's happening (from one or two words to a long list)
 
-For convenience, you can use these datasets (will be uploaded soon), which contain descriptions for most characters represented in booru galleries.
+For convenience, you can use [BooruCharacters_v0.5](https://huggingface.co/datasets/Minthy/BooruCharacters_v0.5) dataset, that contains descriptions for most characters represented in booru galleries.
 
 ### Multiple Caption Formats