sync: main to dev #144
Merged
sync: main to dev #144
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
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
* initial commit for lora dpo Signed-off-by: Jiaqi Zeng <[email protected]> * Lora for SFT/SteerLM (#97) * initial commit: peft for sft Signed-off-by: Jiaqi Zeng <[email protected]> * lora only Signed-off-by: Jiaqi Zeng <[email protected]> * formatting Signed-off-by: Jiaqi Zeng <[email protected]> * minor change Signed-off-by: Jiaqi Zeng <[email protected]> * add assertion Signed-off-by: Jiaqi Zeng <[email protected]> * default to full sft Signed-off-by: Jiaqi Zeng <[email protected]> * enable O2 for lora Signed-off-by: Jiaqi Zeng <[email protected]> * update CHANGELOG.md Signed-off-by: Jiaqi Zeng <[email protected]> * move peft initialization to train_script_utils.py Signed-off-by: Jiaqi Zeng <[email protected]> * remove check for distributed_fused_adam & move setup_complete to init_peft Signed-off-by: Jiaqi Zeng <[email protected]> * update Dockerfile Signed-off-by: Jiaqi Zeng <[email protected]> * fix cherry-pick commit id Signed-off-by: Jiaqi Zeng <[email protected]> --------- Signed-off-by: Jiaqi Zeng <[email protected]> * load_from_nemo bug fix (#103) Signed-off-by: Jiaqi Zeng <[email protected]> * use init_peft Signed-off-by: Jiaqi Zeng <[email protected]> * change default to full tuning Signed-off-by: Jiaqi Zeng <[email protected]> * remove duplicates Signed-off-by: Jiaqi Zeng <[email protected]> * update CHANGELOG.md Signed-off-by: Jiaqi Zeng <[email protected]> * address comments Signed-off-by: Jiaqi Zeng <[email protected]> * update documentation Signed-off-by: Jiaqi Zeng <[email protected]> --------- Signed-off-by: Jiaqi Zeng <[email protected]>
Fixes #145 Signed-off-by: Olivier Delalleau <[email protected]>
github-actions
bot
added
documentation
Signed-off-by: Olivier Delalleau <[email protected]>
Signed-off-by: Gerald Shen <[email protected]> Co-authored-by: Olivier Delalleau <[email protected]>
* fix confusion on checkpoint to use Signed-off-by: Gerald Shen <[email protected]> * fix typo Signed-off-by: Gerald Shen <[email protected]> --------- Signed-off-by: Gerald Shen <[email protected]>
Signed-off-by: Gerald Shen <[email protected]>
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.
sync-branches: New code has just landed in main, so let's bring dev up to speed!