from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("thinkwee/NOVER1-Qwen3-4B")tokenizer = AutoTokenizer.from_pretrained("thinkwee/NOVER1-Qwen3-4B") question = "What is machine learning?" messages = [ { "role": "user", "content": f"Question: {question}\n\nAnswer the question and return in the following format:\n\n<reasoning>\n...\n</reasoning>\n\n<answer>\n...\n</answer>" }] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt")outputs = model.generate(**inputs, max_length=1024, temperature=0.7, do_sample=True)response = tokenizer.decode(outputs[0], skip_special_tokens=True) assistant_start = response.find("assistant\n")assistant_response = response[assistant_start + len("assistant\n"):]print(assistant_response)