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

Fix use_parallel_residual and qkv_bias for StableLM GGUF config extraction #34450

Merged
merged 3 commits into from
Nov 5, 2024

Conversation

Isotr0py
Copy link
Contributor

What does this PR do?

Fixes #34426 (issue)

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.

@VladOS95-cyber @SunMarc

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 fixing this @Isotr0py !

@SunMarc SunMarc requested a review from LysandreJik October 28, 2024 15:00
@VladOS95-cyber
Copy link
Contributor

Hey @Isotr0py! These changes are good to me. Thank you! Please, fix test_stablelm_weights_conversion_fp16 and test_stablelm_fp16 in test_ggml.py as well to get rid of config=original_model.config as we do not need it anymore

Copy link
Member

@LysandreJik LysandreJik left a comment

Choose a reason for hiding this comment

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

Thank you!

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@SunMarc
Copy link
Member

SunMarc commented Nov 5, 2024

Can you try to rebase your PR in order to pass the CI @Isotr0py ?

@Isotr0py
Copy link
Contributor Author

Isotr0py commented Nov 5, 2024

@SunMarc I have merged the main branch but seems that the test CI is still failing in unrelated tests:
https://app.circleci.com/pipelines/github/huggingface/transformers/110104/workflows/8e77c517-3ae4-4cad-ac75-c4ba5616e9d6/jobs/1464043/tests

@VladOS95-cyber
Copy link
Contributor

VladOS95-cyber commented Nov 5, 2024

@SunMarc I have merged the main branch but seems that the test CI is still failing in unrelated tests: https://app.circleci.com/pipelines/github/huggingface/transformers/110104/workflows/8e77c517-3ae4-4cad-ac75-c4ba5616e9d6/jobs/1464043/tests

Hey, try to do rebase. First of all, in command line, git fetch upstream
git rebase upstream/main and then git push -u origin gguf-fix-stablelm --force

@SunMarc
Copy link
Member

SunMarc commented Nov 5, 2024

The problematic test should have been fixed by #34605. Can you try to rebase on that ?

@Isotr0py
Copy link
Contributor Author

Isotr0py commented Nov 5, 2024

@SunMarc All tests passed now!

@SunMarc
Copy link
Member

SunMarc commented Nov 5, 2024

Niceee !

@SunMarc SunMarc merged commit e83aaaa into huggingface:main Nov 5, 2024
26 checks passed
@Isotr0py Isotr0py deleted the gguf-fix-stablelm branch November 8, 2024 15:38
BernardZach pushed a commit to BernardZach/transformers that referenced this pull request Dec 5, 2024
…xtraction (huggingface#34450)

* fix stablelm qkv_bias

* fix stablelm qkv_bias and use_parallel_residual

* remove original_model.config for stablelm gguf test
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.

Stablelm-2-1_6b-chat config extracted from GGUF file differs from source model config
5 participants