Fix example.

README.md

@@ -28,7 +28,11 @@ xlstm = AutoModelForCausalLM.from_pretrained("NX-AI/xLSTM-7b", device_map="auto"
 # this is a fork of EleutherAI/gpt-neox-20b
 tokenizer = AutoTokenizer.from_pretrained("NX-AI/xLSTM-7b")
 
-xlstm(tokenizer("Hello xLSTM, how are you doing?"))
+tokens = tokenizer("Hello xLSTM, how are you doing?", return_tensors='pt')['input_ids'].to(device="cuda")
+
+out = xlstm.generate(tokens, max_new_tokens=20)
+
+print(tokenizer.decode(out[0]))
 ```
 
 ## Speed results