Update README.md

README.md

@@ -1 +1,51 @@
-"Hello" 
+---
+language: multilingual
+tags:
+- text-classification
+- pytorch
+- nli
+- xnli
+- de
+datasets:
+- xnli
+
+pipeline_tag: zero-shot-classification
+
+---
+
+# German Zeroshot
+
+## Model Description
+
+This model has [GBERT Large](https://huggingface.co/deepset/gbert-large) as base model and fine-tuned it on xnli de dataset
+
+#### Zero-shot classification pipeline
+
+```python
+from transformers import pipeline
+classifier = pipeline("zero-shot-classification",
+                      model="Sahajtomar/German_Zeroshot")
+
+# we will classify the Russian translation of, "Who are you voting for in 2020?"
+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
+
+classifier(sequence, candidate_labels, hypothesis_template=hypothesis_template)
+# {'labels': ['politics', 'Europe', 'public health'],
+#  'scores': [0.9048484563827515, 0.05722189322113991, 0.03792969882488251],
+#  'sequence': 'За кого вы голосуете в 2020 году?'}
+```
+
+The default hypothesis template is the English, `This text is {}`. If you are working strictly within one language, it
+may be worthwhile to translate this to the language you are working with:
+
+```python
+sequence_to_classify = "¿A quién vas a votar en 2020?"
+candidate_labels = ["Europa", "salud pública", "política"]
+hypothesis_template = "Este ejemplo es {}."
+classifier(sequence_to_classify, candidate_labels, hypothesis_template=hypothesis_template)
+"""{'labels': ['Tragödie', 'Verbrechen', 'Stehlen'],
+ 'scores': [0.8328856854438782, 0.10494536352157593, 0.06316883927583696],
+ 'sequence': 'Letzte Woche gab es einen Selbstmord in einer nahe gelegenen Kolonie'}"""
+```