-
Notifications
You must be signed in to change notification settings - Fork 2.1k
fix: support dict access in SFT Trainer #3677
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
Conversation
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. |
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
thanks @jannisborn one more formatting left... perhaps easiest if you run |
Thanks @kashif for catching this, the format-on-save in my IDE reorganized the entire file, so I had to disable it. Should be fixed now! |
@jannisborn yes the formatting is tricky... still failing |
@jannisborn I believe the CI is failing due to un-releated reasons... I will double check locally |
Indeed @kashif -- it seemed like a network issue, maybe just rerunning the CI will fix it. I rebased to main now |
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
What does this PR do?
Fixes #3641 (issue)
Before submitting
Pull Request section?
to it if that's the case. Unnecessary breaking change in
SFTTrainer._prepare_dataset
from 0.19.0 compared to 0.18.2 #3641Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.