Better sampling parameters in example

README.md

@@ -116,7 +116,7 @@ messages = [
   {"role": "user", "content": "Wie viele Hände hat ein normaler Mensch?"}
 ]
 inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt", add_generation_prompt=True).to(device)
-outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.5, top_p=0.9)
+outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.3, top_p=0.9, repetition_penalty=1.2)
 print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
 ## Training and evaluation data