feat: enable trl's autounwrap #1060
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@winglian , what do you think the state should be for this PR? Do we need a new config to specify not passing model_ref for adapters? |
Your fix should be the default and if someone really wants a second full ref model loaded then there should be a separate option for that. |
NanoCode012
force-pushed
the
feat/dpo_no_ref
branch
from
284672e
to
9f02c8d
Compare
winglian
approved these changes
Jan 11, 2024
NanoCode012
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
For testing currently!Tested working by Teknium.Based on this https://github.com/huggingface/trl/blob/104a02d207b63a4a062882aaff68f2d275493399/trl/trainer/dpo_trainer.py#L691 , trl would unwrap the model if it's a peft model. This should reduce the need to load the model twice.