Update README.md

README.md

@@ -123,7 +123,13 @@ tokenizer = AutoTokenizer.from_pretrained(
 messages = [
     {"role": "user", "content": "Кога е основан Софийският университет?"},
 ]
-input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
+
+input_ids = tokenizer.apply_chat_template(
+  messages,
+  return_tensors="pt",
+  add_generation_prompt=True,
+  return_dict=True
+)
 
 outputs = model.generate(
   **input_ids,