text-generation-webui部署时报错Can't find config.json at 'loras\['chinese-alpaca-lora-13b']'

[qingying6]

loras里本来就没有config.json文件怎么会报这个错呢？？ (llama.cpp-master) d:\tools\text-generation-webui>python server.py --model llama_13b_hf --lora chinese-alpaca-lora-13b --gpu-memory 6 Gradio HTTP request redirected to localhost :) Loading llama_13b_hf... Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 3/3 [03:36<00:00, 72.13s/it] Loaded the model in 218.80 seconds. Applying the following LoRAs to llama_13b_hf: chinese-alpaca-lora-13b ---------['chinese-alpaca-lora-13b']----------- Traceback (most recent call last): File "D:\python3\llama.cpp-master\lib\site-packages\peft\utils\config.py", line 99, in from_pretrained config_file = hf_hub_download(pretrained_model_name_or_path, CONFIG_NAME) File "D:\python3\llama.cpp-master\lib\site-packages\huggingface_hub\utils_validators.py", line 112, in _inner_fn validate_repo_id(arg_value) File "D:\python3\llama.cpp-master\lib\site-packages\huggingface_hub\utils_validators.py", line 157, in validate_repo_id raise HFValidationError(f"Repo id must be a string, not {type(repo_id)}: '{repo_id}'.") huggingface_hub.utils._validators.HFValidationError: Repo id must be a string, not <class 'pathlib.WindowsPath'>: 'loras['chinese-alpaca-lora-13b']'.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "d:\tools\text-generation-webui\server.py", line 919, in add_lora_to_model([shared.args.lora]) File "d:\tools\text-generation-webui\modules\LoRA.py", line 44, in add_lora_to_model shared.model = PeftModel.from_pretrained(shared.model, Path(f"{shared.args.lora_dir}/{lora_names}"), **params) File "D:\python3\llama.cpp-master\lib\site-packages\peft\peft_model.py", line 135, in from_pretrained config = PEFT_TYPE_TO_CONFIG_MAPPING[PeftConfig.from_pretrained(model_id).peft_type].from_pretrained(model_id) File "D:\python3\llama.cpp-master\lib\site-packages\peft\utils\config.py", line 101, in from_pretrained raise ValueError(f"Can't find config.json at '{pretrained_model_name_or_path}'") ValueError: Can't find config.json at 'loras['chinese-alpaca-lora-13b']'

[lucoo01]

同问

[iMountTai]

peft版本是多少？

[lucoo01]

后面我合并模型后再次运行就可以了

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.

[github-actions[bot]]

Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.