Skip to content

Add conversion from FP32 quants to FP16 quants model #1562

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
Closed
wants to merge 1 commit into from
Closed

Add conversion from FP32 quants to FP16 quants model #1562

wants to merge 1 commit into from

Conversation

Jason0214
Copy link

@Jason0214 Jason0214 commented May 22, 2023 •
edited
Loading

  • Move file_version checking to the front of tensor data loading, so that any broken tensor data won't be parsed, and file_version checking can do its job.
  • Add fp32 to fp16 conversion for Q4_0 and Q4_1 tensors.

At least the file version check should be fixed. Give a try on the conversion by the way.

@Jason0214
Add conversion from FP32 quants to FP16 quants model
ee9aaaa 
- Move file_version checking to the front of tensor data loading, so
  that any broken tensor data won't be parsed, and file_version checking
can do its job.
- Add fp32 to fp16 conversion for Q4_0 and Q4_1 tensors.
@Jason0214 Jason0214 closed this May 22, 2023
@Bearsaerker Bearsaerker mentioned this pull request Mar 12, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@Jason0214