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

Configurable quantization level, fix for broken toggles in model settings #409

Merged
merged 2 commits into from
Jul 19, 2023

Conversation

nkpz
Copy link

@nkpz nkpz commented Jul 19, 2023

  • Removes the 4bit toggle and replaces it with a quantization dropdown which can hold the values "none" | "4bit" | "8bit"
  • Fix an issue where toggles were not turning off correctly due to the value property being checked instead of the checked property. To reproduce the issue, select any <input type="checkbox" data-toggle="toggle"> in an inspector and notice that $0.value is always "on" regardless of the UI state.

@henk717
Copy link
Owner

henk717 commented Jul 19, 2023

Very nice, basically what I would have done.

@henk717 henk717 merged commit dc4404f into henk717:united Jul 19, 2023
FunkEngine2023 pushed a commit to FunkEngine2023/KoboldAI-united that referenced this pull request Jan 7, 2024
Updated Model list and description in Read.md and GPU.ipynb markdown
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

Successfully merging this pull request may close these issues.

2 participants