load new models to fastchat

I have been using a new model that claimed to be built upon fastchat,
I have downloaded all these models file and put them into the folder but they still won't work out
https://huggingface.co/jamessyx/pathasst_caption_tool/tree/main

I have succesfully run the fastchat default model,
When I run the following
python3 -m fastchat.serve.cli --model /location-to-/pathasst_caption_tool --device mps
I have errors like,
Traceback (most recent call last):
File "/opt/homebrew/lib/python3.11/site-packages/peft/config.py", line 100, in from_pretrained
config_file = hf_hub_download(
^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 110, in _inner_fn
validate_repo_id(arg_value)
File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 158, in validate_repo_id
raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/location/pathasst_caption_tool'. Use repo_type argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code

File "/Users/bidetime/Research/Projects/FastChat/fastchat/model/model_adapter.py", line 520, in load_model
config = PeftConfig.from_pretrained(model_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/peft/config.py", line 104, in from_pretrained
raise ValueError(f"Can't find '{CONFIG_NAME}' at '{pretrained_model_name_or_path}'")
ValueError: Can't find 'adapter_config.json' at '/pathasst_caption_tool/'

I don't know where fastchat used to save the models under lmsys/ so it was difficult to find solutions for it. Please help.

Start by reproducing the command python3 -m fastchat.serve.cli --model /location-to-/pathasst_caption_tool --device mps and read fastchat/model/model_adapter.py around line 520. Check how the CLI passes the local model path to PeftConfig.from_pretrained and compare it with the downloaded model files, especially adapter_config.json. Done means the supported loading behavior or the missing model-file requirement is documented or addressed.