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

stack_llama: update instructions in README, fix broken _get_submodules and save tokenizer #358

Merged
merged 3 commits into from
May 11, 2023
Merged

stack_llama: update instructions in README, fix broken _get_submodules and save tokenizer #358

merged 3 commits into from
May 11, 2023

Conversation

teticio
Copy link
Contributor

@teticio teticio commented May 11, 2023 •
edited
Loading

  • The parameter names for merge_peft_adapter.py are out of date in the README
  • LlamaModelForCausalLM does not have an attribute _get_submodules

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented May 11, 2023 •
edited
Loading

The documentation is not available anymore as the PR was closed or merged.

younesbelkada
younesbelkada approved these changes May 11, 2023
View reviewed changes
Copy link
Contributor

@younesbelkada younesbelkada left a comment •
edited
Loading

Choose a reason for hiding this comment

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

This looks good to me! Indeed, in the latest release of peft the _get_submodules method have been moved to peft.utils, can you maybe add a note on the README you modified that the script needs to be run for peft>=0.3.0?

@younesbelkada younesbelkada requested a review from lvwerra May 11, 2023 09:15
@teticio
Copy link
Contributor Author

teticio commented May 11, 2023

  • Also save tokenizer in merge_peft_adapter.py

@teticio
Copy link
Contributor Author

teticio commented May 11, 2023

Wow, you are super quick! Thanks

@teticio
Copy link
Contributor Author

teticio commented May 11, 2023

I'd like to say thank you for putting this repo together. I have been concerned about the likes of ChatGPT taking away the ability to fine-tune models for specific tasks and this is a great piece of work towards democratizing NLP.

@teticio teticio changed the title stack_llama: update instructions in README and fix broken _get_submodules stack_llama: update instructions in README, fix broken _get_submodules and save tokenizer May 11, 2023
younesbelkada
younesbelkada approved these changes May 11, 2023
View reviewed changes
Copy link
Contributor

@younesbelkada younesbelkada left a comment

Choose a reason for hiding this comment

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

Thanks again!

@younesbelkada younesbelkada merged commit dec9993 into huggingface:main May 11, 2023
@dayL-W
Copy link

dayL-W commented May 18, 2023

  • Also save tokenizer in merge_peft_adapter.py

same problem, but my peft==0.3.0

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

@younesbelkada younesbelkada younesbelkada approved these changes

@lvwerra lvwerra Awaiting requested review from lvwerra

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

Successfully merging this pull request may close these issues.
4 participants
@teticio @HuggingFaceDocBuilderDev @dayL-W @younesbelkada