Update README.md

README.md

@@ -17,7 +17,8 @@ pipeline_tag: zero-shot-classification
 
 ## Model Description
 
-This model has [GBERT Large](https://huggingface.co/deepset/gbert-large) as base model and fine-tuned it on xnli de dataset
+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.
 
 #### Zero-shot classification pipeline
 
@@ -25,8 +26,6 @@ This model has [GBERT Large](https://huggingface.co/deepset/gbert-large) as base
 from transformers import pipeline
 classifier = pipeline("zero-shot-classification",
                       model="Sahajtomar/German_Zeroshot")
-##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.
-
 sequence = "Letzte Woche gab es einen Selbstmord in einer nahe gelegenen kolonie"
 candidate_labels = ["Verbrechen","Tragödie","Stehlen"]
 hypothesis_template = "In deisem geht es um {}."    ## Since monolingual model,its sensitive to hypothesis template. This can be experimented