Update README.md

README.md

@@ -5,7 +5,7 @@ language:
 ---
 
 ## Model description
-This model is a fine-tuned version of the [BERT-base-german-cased model by deepset](https://huggingface.co/bert-base-german-cased) to classify German-language toxic comments. 
+This model is a fine-tuned version of the [bert-base-german-cased model by deepset](https://huggingface.co/bert-base-german-cased) to classify German-language toxic comments. 
 
 ## How to use
 
@@ -27,7 +27,7 @@ print(pipeline('du bist blöd.'))
 
 ## Training data
 
-The pre-trained model bert-base-german-cased by deepset.ai was fine-tuned on a crowd-annotated data set of over 14,000 user comments.
+The pre-trained model [bert-base-german-cased model by deepset](https://huggingface.co/bert-base-german-cased) was fine-tuned on a crowd-annotated data set of over 14,000 user comments that has been labeled for toxicity in a binary classification task.
 
 ## Training procedure