Update README.md

README.md

@@ -17,7 +17,7 @@ pipeline_tag: zero-shot-classification
 
 widget:
 
-- text: "Ich habe ein Problem mit meinem Iphone das so schnell wie möglich gelöst werden muss."
+- text: "Ich habe ein Problem mit meinem Iphone, das so schnell wie möglich gelöst werden muss."
 
   candidate_labels: "Computer, Handy, Tablet, dringend, nicht dringend"
 
@@ -25,6 +25,27 @@ widget:
 
 ---
 
+# SVALabs - Gbert Large Zeroshot Nli  
+
+In this repository, we present our german zeroshot model. 
+
+This model was trained on the basis of the German BERT large model from [deepset.ai](https://huggingface.co/deepset/gbert-large) and finetuned as a cross-encoder for Passage Retrieval using the [sentence-transformers](https://github.com/UKPLab/sentence-transformers) package.
+
+For this purpose, we translated the [MSMARCO-Passage-Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) dataset using the [fairseq-wmt19-en-de](https://github.com/pytorch/fairseq/tree/master/examples/wmt19) translation model.
+
+### Model Details
+
+| | Description or Link  |
+
+|---|---|
+
+|**Base model**   | [```german-nlp-group/electra-base-german-uncased```](https://huggingface.co/german-nlp-group/electra-base-german-uncased)  |
+
+|**Finetuning task**| Passage Retrieval / Semantic Search  |
+
+|**Source dataset**| [```MSMARCO-Passage-Ranking```](https://github.com/microsoft/MSMARCO-Passage-Ranking)  |
+
+|**Translation model**|  [```fairseq-wmt19-en-de```](https://github.com/pytorch/fairseq/tree/master/examples/wmt19)  |
 
 DESCRIPTION GOES HERE: 
 Satz 1: