Update README.md

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+language: de
 tags:
 - generated_from_trainer
 datasets:
@@ -7,6 +8,16 @@ datasets:
 model-index:
 - name: ner-bert-german
   results: []
+examples: null
+widget:
+- text: "Herr Schmidt lebt in Berlin und arbeitet für die UN."
+  example_title: Schmidt aus Berlin
+- text: "Die Deutsche Bahn hat ihren Hauptsitz in Frankfurt."
+  example_title: Deutsche Bahn
+- text: "In München gibt es viele Unternehmen, z.B. BMW und Siemens."
+  example_title: München
+metrics:
+- seqeval
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +25,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner-bert-german
 
-This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the wikiann dataset.
+This model can be used to do [named-entity recognition](https://en.wikipedia.org/wiki/Named-entity_recognition) in German. 
+It is trained on a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the German wikiann dataset.
+
 It achieves the following results on the evaluation set:
 - Loss: 0.2450
 - Overall Precision: 0.8767
@@ -69,4 +82,4 @@ The following hyperparameters were used during training:
 - Transformers 4.25.1
 - Pytorch 1.13.1
 - Datasets 2.8.0
-- Tokenizers 0.13.2
+- Tokenizers 0.13.2