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

add DPO and SFT of TRL support in Gaudi and example #601

Merged
merged 2 commits into from
Dec 25, 2023
Merged

add DPO and SFT of TRL support in Gaudi and example #601

merged 2 commits into from
Dec 25, 2023

Conversation

sywangyi
Copy link
Collaborator

What does this PR do?

Fixes # (issue)

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

@sywangyi sywangyi requested a review from regisss as a code owner December 15, 2023 06:09
@sywangyi
Copy link
Collaborator Author

should work with #600

@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.

@sywangyi
Copy link
Collaborator Author

@regisss do we have plan to enable TRL in Gaudi? I have enabled PPO, DPO and SFT by my side. If we have the plan. I will upload the PR one by one.

@sywangyi
Copy link
Collaborator Author

add @libinta for comment

@sywangyi sywangyi force-pushed the trl_dpo branch 2 times, most recently from 6a016a3 to a2d0927 Compare December 20, 2023 10:54
Copy link
Collaborator

@libinta libinta left a comment

Choose a reason for hiding this comment

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

can you add a link in each .py file to specify where this file is ported from and the version also?

@sywangyi
Copy link
Collaborator Author

sywangyi commented Dec 25, 2023

can you add a link in each .py file to specify where this file is ported from and the version also?

done,also upgrade the trl to the latest tag, v0.7.6

@libinta libinta merged commit 79f6de3 into main Dec 25, 2023
9 checks passed
@regisss regisss deleted the trl_dpo branch January 3, 2024 18:11
dsocek pushed a commit to dsocek/optimum-habana that referenced this pull request Jan 4, 2024
* add DPO and SFT of TRL support in Gaudi and example

Signed-off-by: Wang, Yi A <[email protected]>

* upgrade SFTTrainer/DPO trainer and stack_llama_2 example to v0.7.6

Signed-off-by: Wang, Yi A <[email protected]>

---------

Signed-off-by: Wang, Yi A <[email protected]>
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