StackLLaMA: correctly merge peft model #398
Merged
Conversation
This file contains hidden or 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
correctly merge weights with peft's merge_and_unload load sequence classification model for reward models
Closed
|
The documentation is not available anymore as the PR was closed or merged. |
Contributor
younesbelkada
left a comment
younesbelkada
left a comment
There was a problem hiding this comment.
Amazing work @mnoukhov !
Could you run the styling checks?
make style && make qualityAfter that we should be good for merging
Thanks!
Contributor
Author
|
Done! |
lvwerra
approved these changes
Jun 5, 2023
yxliu-TAMU
pushed a commit
to mincheolseong/ECEN743-GRPO-Project-Proposal
that referenced
this pull request
Apr 20, 2025
* correctly merge stackllama models correctly merge weights with peft's merge_and_unload load sequence classification model for reward models * style, black line length 119 * flake8
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
fixes #368 #386 #297 and partially #327
correctly merge weights with peft's
merge_and_unloadif merging a reward model, load
sequence classificationNote that
trl-lib/llama-7b-se-rm-peftdoes not contain thescoreweight so I will release my own pretrained reward model adapter weights