Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes Unsloth-related trainer configuration issues in the fine-tuning CLI by avoiding passing group_by_length into Unsloth’s patched SFTConfig, while keeping existing behavior for the standard Hugging Face/TRL path.
Changes:
- Refactors SFT/QLoRA trainer argument construction to build
SFTConfigfrom a kwargs dict. - Conditionally includes
group_by_lengthonly when PEFT is not already applied (i.e., non-Unsloth path).
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| ModelForge/strategies/sft_strategy.py | Builds SFTConfig via sft_kwargs and avoids group_by_length when Unsloth pre-applied PEFT is detected. |
| ModelForge/strategies/qlora_strategy.py | Mirrors the same conditional group_by_length handling for QLoRA’s SFTConfig. |
You can also share your feedback on Copilot code review. Take the survey.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix bugs in the CLI