How to run this??

[GrommasX]

Hello. last year i use this webui, and no problem. But now - this dosent work with any model! I download any type, ant w8, and when i try to load model - errors again and again, Different errors, but one common thing is - models dont work with it. I download from huggingface any type of text gen model but anyway.. Last year i use wizard 30b, and it was goiod. But now..

[TheLounger]

You gotta post some logs/error messages if you expect anyone to be able to know what the problem is.

[GrommasX]

For example. But problem is not with that model, somethink was changed in this WebUI and now this just dont work. Last year i has no problem with it. But after some update i see many peoples ask about new problems with model loading.

[GrommasX]

Traceback (most recent call last):

File "C:\Users\PC\Downloads\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\configuration_utils.py", line 716, in _get_config_dict

config_dict = cls._dict_from_json_file(resolved_config_file)

          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\PC\Downloads\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\configuration_utils.py", line 814, in _dict_from_json_file

text = reader.read()

   ^^^^^^^^^^^^^

File "", line 322, in decode

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x86 in position 190024: invalid start byte

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

File "C:\Users\PC\Downloads\text-generation-webui-main\modules\ui_model_menu.py", line 245, in load_model_wrapper

shared.model, shared.tokenizer = load_model(selected_model, loader)

                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\PC\Downloads\text-generation-webui-main\modules\models.py", line 87, in load_model

output = load_func_maploader

     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\PC\Downloads\text-generation-webui-main\modules\models.py", line 140, in huggingface_loader

config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=params['trust_remote_code'])

     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\PC\Downloads\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 1138, in from_pretrained

config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)

                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\PC\Downloads\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\configuration_utils.py", line 631, in get_config_dict

config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)

                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\PC\Downloads\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\configuration_utils.py", line 719, in _get_config_dict

raise EnvironmentError(

OSError: It looks like the config file at 'models\model.safetensors' is not a valid JSON file.

[TheLounger]

Model (and all it's accompanying files) should be in a sub-directory, so it's like models\YourModelName\model.safetensors
The built-in downloader actually does this properly.