Update README.md

README.md

@@ -43,21 +43,21 @@ We used the gradient SLURP method.
 
 
 - **Model Type:** SauerkrautLM-7b-HerO is an auto-regressive language model based on the transformer architecture 
-- **Language(s):** English 
+- **Language(s):** English, German
 - **License:** APACHE 2.0
 - **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:[email protected])
 
 **Prompt Template:**
 ```
 <|im_start|>system
-You are Sauerkraut-HerO, a great language model that answers politely and competently. Write down your thoughts step by step to solve problems meaningfully.
+Du bist Sauerkraut-HerO, ein großes Sprachmodell, das höflich und kompetent antwortet. Schreibe deine Gedanken Schritt für Schritt auf, um Probleme sinnvoll zu lösen.
 <|im_end|>
 <|im_start|>user
-How are you?<|im_end|>
+Wie geht esd dir?<|im_end|>
 <|im_start|>assistant
-I am doing well!<|im_end|>
+Mir geht es gut!<|im_end|>
 <|im_start|>user
-Please tell me about how merged models can benefit from existent top-models.<|im_end|>
+Bitte erkläre mir, wie die Zusammenführung von Modellen durch bestehende Spitzenmodelle profitieren kann.<|im_end|>
 <|im_start|>assistant
 ```
 ## Evaluation