Update README.md

README.md

@@ -45,8 +45,10 @@ text = tokenizer.apply_chat_template(
 model_inputs = tokenizer([text], return_tensors="pt").to(device)
 
 generated_ids = model.generate(
-    model_inputs.input_ids,
-    max_new_tokens=4096
+        model_inputs.input_ids,
+        max_new_tokens=4096,
+        do_sample=True,
+        temperature=0.3
 )
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)