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 use_dora and init_lora_weights to ModelConfig and get_peft_config #2406

Open
hommayushi3 opened this issue Nov 28, 2024 · 1 comment
Open

Add use_dora and init_lora_weights to ModelConfig and get_peft_config #2406

hommayushi3 opened this issue Nov 28, 2024 · 1 comment
Labels
✨ enhancement New feature or request

Comments

@hommayushi3
Copy link

Feature request

use_dora and init_lora_weights are missing from ModelConfig.

Motivation

use_dora and init_lora_weights are parameters that exist on LoraConfig that do not exist in trl's ModelConfig, so it makes trl less convenient to use with any model training scripts that require these parameters set, including the SmolVLM finetuning script https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb.

Your contribution

Yes, I could submit a PR for this.
@qgallouedec
Copy link
Member

Thanks for the suggestion. Fell free to open a PR to add this

@qgallouedec qgallouedec added the ✨ enhancement New feature or request label Dec 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
✨ enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@hommayushi3 @qgallouedec