Update README.md

README.md

@@ -20,6 +20,12 @@ pipeline_tag: zero-shot-classification
 This model has [GBERT Large](https://huggingface.co/deepset/gbert-large) as base model and fine-tuned it on xnli de dataset.
 The default hypothesis template is in English: `This text is {}`. While using this model , change it to "In deisem geht es um {}." or something different. While inferencing through huggingface api may give poor results as it uses by default english template. Since model is monolingual and not multilingual, hypothesis template needs to be changed accordingly.
 
+## XNLI DEV (german)
+Accuracy: 85.5
+
+## XNLI TEST (german)
+Accuracy: 83.6
+
 #### Zero-shot classification pipeline
 
 ```python