You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Importing an AI model via the web interface does not work, indicating an error related to the bitsandbytes library, and then a CUDA error, look at the logs.
Is there an existing issue for this?
I have searched the existing issues
Reproduction
copied the repository, launched start_windows.bat, selected cpu there, after the installation was completed, launched the same executable file again, then installed the AI model https://huggingface.co/unsloth/Reflection-Llama-3.1-70B through the models tab in the web interface and then pressed the load button. While using the code, I tried to fix the problem myself by downloading bitsandbytes, bitsandbytes-cuda117, bitsandbytes-windows according to the recommendations of chat-gpt.
Screenshot
Logs
Traceback (most recent call last):
File "C:\text-generation-webui-main\modules\ui_model_menu.py", line 232, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\text-generation-webui-main\modules\models.py", line 93, in load_model
output = load_func_map[loader](model_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\text-generation-webui-main\modules\models.py", line 172, in huggingface_loader
model = LoaderClass.from_pretrained(path_to_model, **params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\models\auto\auto_factory.py", line 564, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\modeling_utils.py", line 3669, in from_pretrained
hf_quantizer.validate_environment(
File "C:\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\quantizers\quantizer_bnb_4bit.py", line 82, in validate_environment
validate_bnb_backend_availability(raise_exception=True)
File "C:\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\integrations\bitsandbytes.py", line 558, in validate_bnb_backend_availability
return _validate_bnb_cuda_backend_availability(raise_exception)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\text-generation-webui-main\installer_files\env\Lib\site-packages\transformers\integrations\bitsandbytes.py", line 536, in _validate_bnb_cuda_backend_availability
raise RuntimeError(log_msg)
RuntimeError: CUDA is required but not available forbitsandbytes. Please consider installing the multi-platform enabled version of bitsandbytes, which is currently a workin progress. Please check currently supported platforms and installation instructions at https://huggingface.co/docs/bitsandbytes/main/en/installation#multi-backend
Describe the bug
Importing an AI model via the web interface does not work, indicating an error related to the bitsandbytes library, and then a CUDA error, look at the logs.
Is there an existing issue for this?
Reproduction
copied the repository, launched start_windows.bat, selected cpu there, after the installation was completed, launched the same executable file again, then installed the AI model https://huggingface.co/unsloth/Reflection-Llama-3.1-70B through the models tab in the web interface and then pressed the load button. While using the code, I tried to fix the problem myself by downloading bitsandbytes, bitsandbytes-cuda117, bitsandbytes-windows according to the recommendations of chat-gpt.
Screenshot
Logs
System Info
The text was updated successfully, but these errors were encountered: