运行inference_hf.py遇到的错误不知道怎么解决

[dqy1111]

root@dsw-337780-78cf4f7476-mccgv:/mnt/workspace/ChatGLM3/finetune_demo# python inference_hf.py output/checkpoint-3000/ --prompt "类型#裙版型#显瘦材质#网纱风格#性感裙型#百褶 裙下摆#压褶裙长#连衣裙* 裙衣门襟#拉链裙衣门襟#套头裙款式#拼接裙款式#拉链裙款式#木耳边裙款式#抽褶裙款式#不规则"
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /mnt/workspace/ChatGLM3/finetune_demo/inference_hf.py:50 in main │
│ │
│ 47 │ │ model_dir: Annotated[str, typer.Argument(help='')], │
│ 48 │ │ prompt: Annotated[str, typer.Option(help='')], │
│ 49 ): │
│ ❱ 50 │ model, tokenizer = load_model_and_tokenizer(model_dir) │
│ 51 │ response, _ = model.chat(tokenizer, prompt) │
│ 52 │ print(response) │
│ 53 │
│ │
│ /mnt/workspace/ChatGLM3/finetune_demo/inference_hf.py:30 in load_model_and_tokenizer │
│ │
│ 27 def load_model_and_tokenizer(model_dir: Union[str, Path]) -> tuple[ModelType, TokenizerT │
│ 28 │ model_dir = _resolve_path(model_dir) │
│ 29 │ if (model_dir / 'adapter_config.json').exists(): │
│ ❱ 30 │ │ model = AutoPeftModelForCausalLM.from_pretrained( │
│ 31 │ │ │ model_dir, trust_remote_code=True, device_map='auto' │
│ 32 │ │ ) │
│ 33 │ │ tokenizer_dir = model.peft_config['default'].base_model_name_or_path │
│ │
│ /opt/conda/lib/python3.10/site-packages/peft/auto.py:69 in from_pretrained │
│ │
│ 66 │ │ are passed along to PeftConfig that automatically takes care of filtering the │
│ 67 │ │ the config object init. │
│ 68 │ │ """ │
│ ❱ 69 │ │ peft_config = PeftConfig.from_pretrained(pretrained_model_name_or_path, **kwargs │
│ 70 │ │ base_model_path = peft_config.base_model_name_or_path │
│ 71 │ │ │
│ 72 │ │ task_type = getattr(peft_config, "task_type", None) │
│ │
│ /opt/conda/lib/python3.10/site-packages/peft/config.py:137 in from_pretrained │
│ │
│ 134 │ │ │ config_cls = cls │
│ 135 │ │ │
│ 136 │ │ kwargs = {**class_kwargs, **loaded_attributes} │
│ ❱ 137 │ │ config = config_cls(**kwargs) │
│ 138 │ │ return config │
│ 139 │ │
│ 140 │ @classmethod │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: LoraConfig.init() got an unexpected keyword argument 'layer_replication'

[zRzRzRzRzRzRzR]

更新到最新代码试试？