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

Support dequantizing GGUF FP16 format #31783

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Support dequantizing GGUF FP16 format #31783

wants to merge 2 commits into from
+17 −0

Conversation

PenutChen
Copy link

@PenutChen PenutChen commented Jul 4, 2024 •
edited
Loading

What does this PR do?

Fixes #31762: Supports GGUF integration to dequantize FP16 format.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@SunMarc

SunMarc
SunMarc reviewed Jul 4, 2024
View reviewed changes
Copy link
Member

@SunMarc SunMarc left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for adding this ! Could you add a test to make sure that it works ? You can put it in the tests/quantization/ggml/test_ggml.py file

@PenutChen
Copy link
Author

Thanks for adding this ! Could you add a test to make sure that it works ? You can put it in the tests/quantization/ggml/test_ggml.py file

@SunMarc currently, only TinyLlama has reasonable outputs, but I can't find an FP16 GGUF model on HF Hub. Should I upload one myself?

@SunMarc
Copy link
Member

SunMarc commented Jul 4, 2024

Yes, that would be great !

@PenutChen
Copy link
Author

@SunMarc I've added an f16 test, and the models are now uploaded to the HF Hub. Also, I've uploaded the bf16 and f32 tinyllama for future tests. Let me know if you need anything else!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@SunMarc SunMarc SunMarc left review comments

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Converting gguf fp16 & bf16 to hf is not supported.
2 participants
@PenutChen @SunMarc