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

add the lora target modules for Mistral Models #974

Merged
merged 1 commit into from
Sep 28, 2023
Merged

add the lora target modules for Mistral Models #974

merged 1 commit into from
Sep 28, 2023

Conversation

pacman100
Copy link
Contributor

What does this PR do?

  1. Add the lora target modules for Mistral Models

younesbelkada
younesbelkada approved these changes Sep 28, 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.

Awesome, thanks!

younesbelkada
younesbelkada reviewed Sep 28, 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.

Would it make sense to use k_proj & v_proj to be consistent with llama?

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Sep 28, 2023 •
edited
Loading

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

@pacman100
Copy link
Contributor Author

Would it make sense to use k_proj & v_proj to be consistent with llama?

Hello Younes, for all models, it is Q and V layers as per the LoRA paper.

BenjaminBossan
BenjaminBossan approved these changes Sep 28, 2023
View reviewed changes
Copy link
Member

@BenjaminBossan BenjaminBossan left a comment

Choose a reason for hiding this comment

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

LGTM, thanks for the quick addition.

@younesbelkada
Copy link
Contributor

Oops sorry, I got confused with IA3, could you also add mistral to IA3 and adalora mapping? Can be also done in a follow up PR

@pacman100 pacman100 merged commit f66c385 into main Sep 28, 2023
11 checks passed
@younesbelkada younesbelkada deleted the smangrul/add-mistral-target-modules branch September 28, 2023 09:25
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

@BenjaminBossan BenjaminBossan BenjaminBossan approved these changes

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
@pacman100 @HuggingFaceDocBuilderDev @younesbelkada @BenjaminBossan