-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error when using AWQ model with 'use_gpu_id=False' #1768
Comments
bw-Deejee
changed the title
Error when using AWQ model with 'use_safetensors=True' together with 'hf_embedding_model'
Error when using AWQ model together with 'hf_embedding_model'
Jul 24, 2024
bw-Deejee
changed the title
Error when using AWQ model together with 'hf_embedding_model'
Error when using AWQ model with 'use_gpu_id=False'
Jul 24, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Using the newest version of the repo.
Following command works:
python generate.py --base_model=casperhansen/llama-3-70b-instruct-awq --load_awq=model
following command doesn't:
python generate.py --base_model=casperhansen/llama-3-70b-instruct-awq --load_awq=model --use_gpu_id=False
error message:
... TypeError: functools.partial(<bound method AutoAWQForCausalLM.from_quantized of <class 'awq.models.auto.AutoAWQForCausalLM'>>, fuse_layers=True) got multiple values for keyword argument 'use_safetensors'
Setting
--use_safetensors=True
doesnt help.Is there any way to solve this?
The text was updated successfully, but these errors were encountered: