Update README.md

README.md

@@ -6,16 +6,22 @@ language: German or Deutsch  <br />
 thumbnail: "https://huggingface.co/Tanhim/gpt2-model-de" <br />
 datasets: Ten Thousand German News Articles Dataset <br />
 
-
-* How to use from the 🤗/transformers library <br />
-
+### How to use
+You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
+set a seed for reproducibility:
+```python
+>>> from transformers import pipeline, set_seed
+>>> generation= pipeline('text-generation', model='Tanhim/gpt2-model-de')
+>>> set_seed(42)
+>>> generation("Hallo, ich bin ein Sprachmodell,", max_length=30, num_return_sequences=5)
+
+```
+Here is how to use this model to get the features of a given text in PyTorch:
+```python
 from transformers import AutoTokenizer, AutoModelWithLMHead <br />
-  
 tokenizer = AutoTokenizer.from_pretrained("Tanhim/gpt2-model-de") <br />
 model = AutoModelWithLMHead.from_pretrained("Tanhim/gpt2-model-de") <br />
-
-* How to use from the pipeline <br />
-
-from transformers import pipeline  <br />
-
-text-generation = pipeline("text-generation", model="Tanhim/gpt2-model-de", tokenizer="anonymous-german-nlp/german-gpt2") <br />
+text = "Ersetzen Sie mich durch einen beliebigen Text, den Sie wünschen."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+```