made usage example more copy friendly

README.md

@@ -30,7 +30,17 @@ See the script `evaluate.py` in the [GerPT2 Github repository](https://github.co
 
 ## Usage
 
-![GerPT2 usage](https://user-images.githubusercontent.com/13353204/100330362-288d0b80-2fcf-11eb-82e7-ed71c7140a88.png)
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("benjamin/gerpt2")
+model = AutoModelForCausalLM.from_pretrained("benjamin/gerpt2")
+
+prompt = "<your prompt>"
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+print(pipe(prompt)[0]["generated_text"])
+```
 
 Also, two tricks might improve the generated text: