Update README.md

README.md

@@ -25,6 +25,7 @@ widget:
 
 ---
 
+
 # SVALabs - Gbert Large Zeroshot Nli  
 
 In this repository, we present our german zeroshot model. 
@@ -50,7 +51,7 @@ We evaluated our model for the nli task using the TEST set of the German part of
 XNLI TEST-Set Accuracy: 86% 
 
 
-## Zeroshot Text Classification Task Benchmark 
+### Zeroshot Text Classification Task Benchmark 
 
 We further tested our model for a zeroshot text classification task using a part of the [10kGNAD Dataset](https://tblock.github.io/10kGNAD/).
 Specifically, we used all articles that were labeled "Kultur", "Sport", "Web", "Wirtschaft" und "Wissenschaft". 
@@ -65,10 +66,17 @@ The next table shows the results as well as a comparison with other German langu
 | deepset/gbert-base | 0.65 |
 
 
-## How to use 
+### 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", 
+and select "svalabs/gbert-large-zeroshot-nli" as model. 
 
-The simplest way to use the model is the hugging-face transformers pipeline tool. 
-Just initialize the pipeline specifying the task as "zero-shot-classification" 
+The model requires you to specify labels (ideally labels suited to your task), 
+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. 
+ 
 
 ```python