added prompt to model card

README.md

@@ -71,7 +71,26 @@ Please check manually that your output text corresponds to the input text, as fa
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+We offer two tools to interact with our model: an online app and a browser extension. They can be viewed and used [here](https://publicinterest.ai/tool/simba?lang=en).
+
+Alternatively, to load the model using transformers:
+
+```
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+device = "cuda"
+tokenizer = AutoTokenizer.from_pretrained("hiig-piai/simba_best_092024")
+model = AutoModelForCausalLM.from_pretrained("hiig-piai/simba_best_092024", torch_dtype=torch.float16).to(device)
+```
+
+We used the following prompt at inference to test our model:
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+Du bist ein hilfreicher Assistent und hilfst dem User, Texte besser zu verstehen.<|eot_id|><|start_header_id|>user<|end_header_id|>
+Kannst du bitte den folgenden Text zusammenfassen und sprachlich auf ein A2-Niveau in Deutsch vereinfachen? Schreibe maximal 5 Sätze.
+{input_text}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
 
 [More Information Needed]