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

I updated and it crashes with an error #1538

Closed
intulint opened this issue May 20, 2023 · 4 comments
Closed

I updated and it crashes with an error #1538

intulint opened this issue May 20, 2023 · 4 comments

Comments

@intulint
Copy link

Updated today and does not start. The build will run without errors. I used to make.
Ubuntu 22.04

main: build = 574 (ea60007)
main: seed = 1684581738
llama.cpp: loading model from ../Wizard-Vicuna-7B-Uncensored.ggmlv2.q4_1.bin
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc

@intulint
Copy link
Author

2d5db48 this is the commit that stopped working

@SlyEcho
Copy link
Collaborator

SlyEcho commented May 20, 2023

You need to quantize your model again from F16. the Q4_0, Q4_1 and Q8_0 formats changed.

@intulint
Copy link
Author

@SlyEcho again? I'll have to stay on the working version for now. I understand

@SlyEcho
Copy link
Collaborator

SlyEcho commented May 20, 2023

#1508 is the change. There really should be an error message.

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

No branches or pull requests

2 participants