Update README.md

README.md

@@ -67,16 +67,16 @@ The next table shows the results as well as a comparison with other German langu
 ### How to use 
 
 The simplest way to use the model is the huggingface transformers pipeline tool. 
-Just initialize the pipeline specifying the task as "zero-shot-classification", 
+Just initialize the pipeline specifying the task as "zero-shot-classification" 
 and select "svalabs/gbert-large-zeroshot-nli" as model. 
 
-The model requires you to specify labels (ideally labels suited to your task), 
+The model requires you to specify labels, 
 a sequence (or list of sequences) to classify and a hypothesis template. 
 In our tests, if the labels comprise only single words, 
 "In diesem Satz geht es um das Thema {}" performed the best. 
 
 However, for multiple words, especially when they combine nouns and verbs,
-Simple hypothesis such as "Weil" or "Daher" may perform better. 
+Simple hypothesis such as "Weil {}" or "Daher {}" may work better. 
 
 Here is an example of how to use the model: