lollms-webui
lollms-webui copied to clipboard
missing python package accelerate and autoawq
Expected Behavior
./linux_run.sh
start with no error
Current Behavior
Failed to load model.
Returned exception: 'bool' object has no attribute 'value'
Traceback (most recent call last):
File "/mnt/games_fast/lollms-webui/lollms-webui/lollms_core/lollms/app.py", line 246, in load_model
model = ModelBuilder(self.binding).get_model()
File "/mnt/games_fast/lollms-webui/lollms-webui/lollms_core/lollms/binding.py", line 584, in __init__
self.build_model()
File "/mnt/games_fast/lollms-webui/lollms-webui/lollms_core/lollms/binding.py", line 587, in build_model
self.model = self.binding.build_model()
File "/mnt/games_fast/lollms-webui/lollms-webui/zoos/bindings_zoo/hugging_face/__init__.py", line 243, in build_model
self.model:AutoModelForCausalLM = AutoModelForCausalLM.from_pretrained(str(model_path),
File "/mnt/games_fast/lollms-webui/installer_files/lollms_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 566, in from_pretrained
return model_class.from_pretrained(
File "/mnt/games_fast/lollms-webui/installer_files/lollms_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2863, in from_pretrained
raise ImportError(
ImportError: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/mnt/games_fast/lollms-webui/lollms-webui/lollms_core/lollms/app.py", line 101, in __init__
self.model = self.load_model()
File "/mnt/games_fast/lollms-webui/lollms-webui/lollms_core/lollms/app.py", line 251, in load_model
self.notify("Couldn't load model.", False)
File "/mnt/games_fast/lollms-webui/lollms-webui/api/__init__.py", line 1609, in notify
'notification_type': notification_type.value,
AttributeError: 'bool' object has no attribute 'value'
after installing accelerate: ....
raise ImportError("Loading an AWQ quantized model requires auto-awq library (`pip install autoawq`)")
ImportError: Loading an AWQ quantized model requires auto-awq library (`pip install autoawq`)
Steps to Reproduce
./linux_run.sh
on debian trixie
Possible Solution
installer_files/lollms_env/bin/python -m pip install accelerate
installer_files/lollms_env/bin/python -m pip install autoawq
Context
Please provide any additional context about the issue.
Screenshots
If applicable, add screenshots to help explain the issue.
seems only to come up once you have installed some models
Sorry, I just fixed it. It was the move to the new notification system on lollms that caused this. I forgot to migrate this code to the new format Thanks for the message