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

[xxxTrainer] Add tags to all trainers in TRL #1120

Merged
merged 3 commits into from
Dec 21, 2023
Merged

[xxxTrainer] Add tags to all trainers in TRL #1120

merged 3 commits into from
Dec 21, 2023

Conversation

younesbelkada
Copy link
Contributor

@younesbelkada younesbelkada commented Dec 20, 2023

What does this PR do?

As per title, this PR adds the tag "trl-xxx" whenever someone pushes a model with SFTTrainer, PPOTrainer or DPOTrainer

Example repo here: https://huggingface.co/ybelkada/out-test

cc @lvwerra

@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.

@younesbelkada younesbelkada changed the title [SFTTrainer] Add tags to sfttrainer [xxxTrainer] Add tags to all trainers in TRL Dec 20, 2023
Copy link
Member

@lvwerra lvwerra left a comment

Choose a reason for hiding this comment

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

Looks great! Just to confirm the example only used sft and not trl-sft, right?

@lvwerra
Copy link
Member

lvwerra commented Dec 21, 2023

Also, should we add it for DDPO as well?

@younesbelkada younesbelkada merged commit b07935f into main Dec 21, 2023
9 checks passed
@younesbelkada younesbelkada deleted the add-tags branch December 21, 2023 16:04
@younesbelkada
Copy link
Contributor Author

Done !

lapp0 pushed a commit to lapp0/trl that referenced this pull request May 10, 2024
* add tags to sfttrainer

* extend it to other trainers

* add for ddpo
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.

3 participants