Skip to content
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

[run llama-13b] NameError: name 'cuda_setup' is not defined. Did you mean: 'CUDASetup'? #291

Closed
s1530129650 opened this issue Mar 13, 2023 · 3 comments
Labels

Comments

@s1530129650
Copy link

s1530129650 commented Mar 13, 2023

run python server.py --share --listen --chat --model llama-7b.

Everything is okay.

image

However, when run ```` python server.py --share --listen --chat --model llama-13b ```,

It would report an error: NameError: name 'cuda_setup' is not defined. Did you mean: 'CUDASetup'?

image

@s1530129650
Copy link
Author

s1530129650 commented Mar 13, 2023

fixed by

pip uninstall bitsandbytes
pip install bitsandbytes

refer to bitsandbytes-foundation/bitsandbytes#134.

Another issue
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

image

@Ph0rk0z
Copy link
Contributor

Ph0rk0z commented Mar 13, 2023

You will have to add #198 and set threshold probably between 1 and 1.5 and limit context to where you don't get NaN error or out of memory. For llama 13b I can pull this off, for pythia 12b I cannot.

@github-actions github-actions bot added the stale label Apr 12, 2023
@github-actions
Copy link

This issue has been closed due to inactivity for 30 days. If you believe it is still relevant, please leave a comment below.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants