import torchfrom peft import PeftModelfrom transformers import AutoTokenizer, Qwen3_5ForCausalLM base_id = "Qwen/Qwen3.5-4B"adapter_id = "Shokou1/fanzha-qwen3.5-4b-grpo-v2"tokenizer = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)model = Qwen3_5ForCausalLM.from_pretrained( base_id, trust_remote_code=True, dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id)messages = [{"role": "user", "content": "有人让我把钱转到安全账户自证清白,怎么办?"}]input_ids = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)output = model.generate(input_ids, max_new_tokens=220, do_sample=False)print(tokenizer.decode(output[0, input_ids.shape[-1]:], skip_special_tokens=True))