Update README.md

README.md

@@ -37,7 +37,7 @@ This is a merge of pre-trained language models created using [mergekit](https://
 
 This model was merged using the della_linear merge method using [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) as a base.
 
-The 3 models finetuned by me will not be released. They are trained on my own datasets ([Danoia-v02] and [Danoia-v03] (CC BY 4.0)) to teach them danish. This method seems better than just training a LoRA. To me at least.
+The 3 models finetuned by me will not be released. They are trained on my own datasets to teach them danish. This method finetuning different models and merging them seems to work better for that purpose. To me at least.
 
 ### Models Merged