Skip to content
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

Nemotron5 features #403

Draft
wants to merge 6 commits into
base: main
Choose a base branch
from
Draft

Nemotron5 features #403

wants to merge 6 commits into from

Conversation

arendu
Copy link
Collaborator

@arendu arendu commented Nov 14, 2024

What does this PR do ?

contains changes to support nemotron5

Changelog

  • Please update the CHANGELOG.md under next version with high level changes in this PR.

Usage

  • You can potentially add a usage example below
# Add a code snippet demonstrating how to use this 

Before your PR is "Ready for review"

Pre checks:

Checklist when contributing a new algorithm

  • Does the trainer resume and restore model state all states?
  • Does the trainer support all parallelism techniques(PP, TP, DP)?
  • Does the trainer support max_steps=-1 and validation?
  • Does the trainer only call APIs defined in alignable_interface.py?
  • Does the trainer have proper logging?

Additional Information

  • Related to # (issue)

)

Signed-off-by: Terry Kong <[email protected]>
Signed-off-by: NeMo-Aligner CI <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
@github-actions github-actions bot added documentation Improvements or additions to documentation CI labels Nov 21, 2024
@github-actions github-actions bot removed CI documentation Improvements or additions to documentation labels Nov 21, 2024
wip

Signed-off-by: arendu <[email protected]>

docs: 0.5.0 documentation updates (#346)

Signed-off-by: ashors1 <[email protected]>

ci: Sign-off cherry pick (#366)

Signed-off-by: Oliver Koenig <[email protected]>

docs: main readme and sft docs (#367)

Signed-off-by: Oleksii Kuchaiev <[email protected]>
Co-authored-by: Gerald Shen <[email protected]>

docs: fix code block rendering (#369)

Signed-off-by: ashors1 <[email protected]>

dpo and sft

Signed-off-by: arendu <[email protected]>

dpo support

Signed-off-by: root <[email protected]>

mamba padding

Signed-off-by: arendu <[email protected]>

convenience script to remove old format of DPO data

Signed-off-by: adithyare <[email protected]>

pad to mult 256

Signed-off-by: arendu <[email protected]>

copy dpo style cfg overrides

Signed-off-by: arendu <[email protected]>

remove _modify_config

Signed-off-by: arendu <[email protected]>

fix config issue

Signed-off-by: Jiaqi Zeng <[email protected]>

fix mamba config issue

Signed-off-by: Jiaqi Zeng <[email protected]>

is mamba default false

Signed-off-by: arendu <[email protected]>

revert cherry-pick-release-commit

Signed-off-by: Terry Kong <[email protected]>

Revert "revert cherry-pick-release-commit"

This reverts commit 911337c.

undo .github/workflows

Signed-off-by: Terry Kong <[email protected]>

revert docs changes that weren't supposed to be there

Signed-off-by: Terry Kong <[email protected]>
for more information, see https://pre-commit.ci

Signed-off-by: NeMo-Aligner CI <[email protected]>
Signed-off-by: arendu <[email protected]>
@github-actions github-actions bot added the Utils label Dec 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants