Skip to content

commit dislora #11122

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
Merged
merged 4 commits into from
Oct 22, 2025
Merged

commit dislora #11122

merged 4 commits into from
Oct 22, 2025

Conversation

@Pioneer-wxh
Copy link
Contributor

@Pioneer-wxh Pioneer-wxh commented Sep 26, 2025 •
edited
Loading

Before submitting

  • Lint code. If there are lint issues, please format the code first.
# Install and register `pre-commit` in the project folder
pip install pre-commit && pre-commit install

# Process previous code files separately
pre-commit run --file XXXX.py
  • Add test cases into tests folder. If there are codecov issues, please add tests cases first.

PR types

PR changes

Description

@CLAassistant
Copy link

CLAassistant commented Sep 26, 2025 •
edited
Loading

CLA assistant check
All committers have signed the CLA.

lugimzzz
lugimzzz reviewed Oct 16, 2025
View reviewed changes
llm/run_finetune.py

train_ds, dev_ds, test_ds = create_dataset(data_args, training_args)

train_dataset_size = None
Copy link
Contributor

Choose a reason for hiding this comment

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

为什么需要get datasize?

paddlenlp/trl/sft_trainer.py Outdated
if max_eval_iters > 0 and step >= max_eval_iters - 1:
break

def _calc_ortho_loss(self, model):
Copy link
Contributor

Choose a reason for hiding this comment

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

不要写在SFTTrainer里，peft/dislora目录下新起一个DisLoRATrainer

lugimzzz
lugimzzz approved these changes Oct 22, 2025
View reviewed changes
Copy link
Contributor

@lugimzzz lugimzzz left a comment

Choose a reason for hiding this comment

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

LGTM

@lugimzzz lugimzzz merged commit 51787ba into PaddlePaddle:develop Oct 22, 2025
9 of 10 checks passed
@luotao1
Copy link
Collaborator

luotao1 commented Oct 23, 2025

hi, @Pioneer-wxh

  • 非常感谢你对飞桨的贡献，我们正在运营一个PFCC组织。PFCC是飞桨开源的贡献者俱乐部，只有给飞桨合入过代码的开发者才能加入，俱乐部里每两周会有一次例会（按兴趣参加），也会时不时办线下meetup面基，详情可见 https://github.com/luotao1 主页说明。
  • 如果你对PFCC有兴趣，请发送邮件至 [email protected]，我们会邀请你加入~

AlAuAu pushed a commit to AlAuAu/PaddleNLP that referenced this pull request Oct 23, 2025
@Pioneer-wxh @AlAuAu
commit dislora (PaddlePaddle#11122)
9d12dc2 
* commit dislora

* add DisLoRATrainer

* “readme文件修改”

* Delete docs/zh/llm/benchmark/rl/README.md
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@lugimzzz lugimzzz lugimzzz 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

@Pioneer-wxh @CLAassistant @luotao1 @lugimzzz