8bit loading not working anymore

[FurkanGozukara]

I just did a fresh install and using below code

    if use_8bit:
        text_encoder = T5EncoderModel.from_pretrained(
            model_path,
            subfolder="text_encoder",
            load_in_8bit=True,
            device_map="auto",
        )
        pipe = PixArtAlphaPipeline.from_pretrained(
            model_path,
            text_encoder=text_encoder,
            torch_dtype=torch.float16,
            device_map="auto"
        )

the error i got is as below

Downloading shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<?, ?it/s]
bin G:\temp7\PixArt-alpha\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.dll
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████| 2/2 [00:05<00:00,  2.65s/it]
Loading pipeline components...:  20%|██████████████                                                        | 1/5 [00:01<00:04,  1.11s/it]
Traceback (most recent call last):
  File "G:\temp7\PixArt-alpha\app.py", line 144, in <module>
    pipe = PixArtAlphaPipeline.from_pretrained(
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 118, in _inner_fn
    return fn(*args, **kwargs)
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1275, in from_pretrained
    loaded_sub_model = load_sub_model(
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 525, in load_sub_model
    loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 118, in _inner_fn
    return fn(*args, **kwargs)
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 683, in from_pretrained
    accelerate.load_checkpoint_and_dispatch(
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\accelerate\big_modeling.py", line 555, in load_checkpoint_and_dispatch
    load_checkpoint_in_model(
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\accelerate\utils\modeling.py", line 1550, in load_checkpoint_in_model
    set_module_tensor_to_device(
  File "G:\temp7\PixArt-alpha\venv\lib\site-packages\accelerate\utils\modeling.py", line 301, in set_module_tensor_to_device
    raise ValueError(f"{module} does not have a parameter or a buffer named {tensor_name}.")
ValueError: PixArtAlphaTextProjection(
  (linear_1): Linear(in_features=4096, out_features=1152, bias=True)
  (act_1): GELU(approximate='tanh')
  (linear_2): Linear(in_features=1152, out_features=1152, bias=True)
) does not have a parameter or a buffer named y_embedding.
all started

[FurkanGozukara]

found the error. thankfully i am keeping pip freeze in my auto installers