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.

Sign up for GitHub

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

Jump to bottom

GPTQModel support #1

Closed
Qubitium opened this issue Dec 16, 2024 · 1 comment
Closed

GPTQModel support #1

Qubitium opened this issue Dec 16, 2024 · 1 comment

Comments

@Qubitium
Copy link

Qubitium commented Dec 16, 2024 •
edited
Loading

Please note GPTQModel will be soon merged into transformers/peft/optimum so the same auto-gptq training code will work but adapted using updated GPTQModel kernels and internal code. AutoGPTQ has various reasons, stopped development and GPTQModel is the likely replacement going forward.

Tracking upstream merge here: ModelCloud/GPTQModel#729
@SuperBruceJia
Copy link
Member

Please note GPTQModel will be soon merged into transformers/peft/optimum so the same auto-gptq training code will work but adapted using updated GPTQModel kernels and internal code. AutoGPTQ has various reasons, stopped development and GPTQModel is the likely replacement going forward.

Tracking upstream merge here: ModelCloud/GPTQModel#729

Dear Qubitium and William (Qiwei),

Well received with thanks! We will update our codebase with the development of the GPTQModel.

Best regards,

Shuyue
Dec. 16th, 2024

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Qubitium @SuperBruceJia