I'm unable to load model blockblockblock_LLaMA-33B-HF-bpw4-exl2 using the latest version of oobabooga (Aug 7, 2024)

[pm4user444]

I can load other large models, for example: TheBloke_WizardLM-33B-V1.0-Uncensored-GPTQ with no problems.

When I try to load: blockblockblock_LLaMA-33B-HF-bpw4-exl2 it fails with errors listed below.

I have a 3090 with 24GVR and am running oobabooga via nvidia GPU

Thanks for any assistance you are able to provide, I'm stuck. Thanks again

15:18:03-467302 INFO Loading "blockblockblock_LLaMA-33B-HF-bpw4-exl2"

C:\OggAugTwfour\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\generation\configuration_utils.py:577: UserWarning: do_sample is set to False. However, min_p is set to 0.0 -- this flag is only used in sample-based generation modes. You should set do_sample=True or unset min_p.

warnings.warn(

15:18:54-684724 ERROR Failed to load the model.

Traceback (most recent call last):

File "C:\OggAugTwfour\text-generation-webui-main\modules\ui_model_menu.py", line 231, in load_model_wrapper

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

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

File "C:\OggAugTwfour\text-generation-webui-main\modules\models.py", line 101, in load_model

tokenizer = load_tokenizer(model_name, model)

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

File "C:\OggAugTwfour\text-generation-webui-main\modules\models.py", line 123, in load_tokenizer

tokenizer = AutoTokenizer.from_pretrained(

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

File "C:\OggAugTwfour\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\models\auto\tokenization_auto.py", line 896, in from_pretrained

return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)

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