Update README.md

README.md

@@ -11,40 +11,25 @@ tags:
 - legal
 ---
 
-<h1> Legalis BERT Model </h1>
+# Model description
 
-<h2> Model Details </h2>
+This is a BERT classifiert, trained on a processed dataset of 2800 German court cases (see [legalis dataset](https://huggingface.co/datasets/LennardZuendorf/legalis)). It predicts the winner (defended/"Verklagt*r" or plaintiff/"Kläger*in") of a court case based on facts provided (in German).
 
-<h3> Model Description </h3>
+## Intended uses & limitations
 
-This is a court case prediction model build for a university course, this particular one utalises text classification with 
+- This model was created as part of a university project and should be considered highly experimental.
 
-- **Developed by:** Lennard Zündorf
-- **Model type:** transformer-based
-- **Language(s) (NLP):** German 
-- **Finetuned from model :** [German BERT/ gbert-base](https://huggingface.co/deepset/gbert-base)
+## get started with the model
 
-<h3> Model Sources </h3>
+Try out the hosted Interference UI or the [Huggingface Space](https://huggingface.co/spaces/LennardZuendorf/legalis)
 
-- **Repository:** [GitHub](https://github.com/LennardZuendorf/legalis)
-- **Demo:** on [Huggingface](https://huggingface.co/spaces/LennardZuendorf/legalis)
+# Model Card Authors
 
-<h2> Uses </h2>
+This model card and the model itself are written by following authors:
 
-You can use this model to try and predict the outcome of a court case based on the legal facts.
+[@LennardZuendorf -HGF](https://huggingface.co/LennardZuendorf)
+[@LennardZuendorf - Github](https://github.com/LennardZuendorf)
 
-<h2> Training Details </h2>
+# Citation
 
-<h3>Training Data
-
-This model uses the similarly named [dataset](https://huggingface.co/models?dataset=dataset:LennardZuendorf/legalis)
-
-<h3> Testing Data & Metrics
-
-<h4> Metrics </h4>
-
-There has not been any testing yet.
-
-<h3> Results </h3>
-
-The accuracy score against the testing split is as high as 0.60
+See Dataset for Sources and refer to [Github](https://github.com/LennardZuendorf/uniArchive-legalis) for collection of all files.