Not loading after latest config changes?

#26
by Novelo - opened

I been geting the following errors after I pull latest from both this repo and oobabooga:

Traceback (most recent call last): File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\transformers\configuration_utils.py”, line 659, in _get_config_dict config_dict = cls._dict_from_json_file(resolved_config_file) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\transformers\configuration_utils.py”, line 751, in dict_from_json_file return json.loads(text) File "D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\json_init.py", line 346, in loads return _default_decoder.decode(s) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\json\decoder.py”, line 340, in decode raise JSONDecodeError(“Extra data”, s, end) json.decoder.JSONDecodeError: Extra data: line 25 column 2 (char 595)

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File “D:\Projects\AI\TextGeneration\oobabooga_windows\text-generation-webui\server.py”, line 68, in load_model_wrapper shared.model, shared.tokenizer = load_model(shared.model_name, loader) File “D:\Projects\AI\TextGeneration\oobabooga_windows\text-generation-webui\modules\models.py”, line 78, in load_model output = load_func_maploader File “D:\Projects\AI\TextGeneration\oobabooga_windows\text-generation-webui\modules\models.py”, line 292, in AutoGPTQ_loader return modules.AutoGPTQ_loader.load_quantized(model_name) File “D:\Projects\AI\TextGeneration\oobabooga_windows\text-generation-webui\modules\AutoGPTQ_loader.py”, line 56, in load_quantized model = AutoGPTQForCausalLM.from_quantized(path_to_model, **params) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\auto_gptq\modeling\auto.py”, line 79, in from_quantized model_type = check_and_get_model_type(save_dir or model_name_or_path, trust_remote_code) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\auto_gptq\modeling_utils.py”, line 123, in check_and_get_model_type config = AutoConfig.from_pretrained(model_dir, trust_remote_code=trust_remote_code) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\transformers\models\auto\configuration_auto.py”, line 944, in from_pretrained config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\transformers\configuration_utils.py”, line 574, in get_config_dict config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) File “D:\Projects\AI\TextGeneration\oobabooga_windows\installer_files\env\lib\site-packages\transformers\configuration_utils.py”, line 662, in _get_config_dict raise EnvironmentError( OSError: It looks like the config file at ‘models\TheBloke_guanaco-65B-GPTQ\config.json’ is not a valid JSON file.

Can you try downloading the repo again. I can't see anything wrong with the config.json, and it doesn't even have 25 lines in it. I'm wondering if you've got some corruption or bad download or something.

If you download again in text-generation-webui it won't re-download everything, just anything that's changed.

Sign up or log in to comment