Skip to content

Use llm export for refit #435

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

Draft
wants to merge 4 commits into
base: sahilj/megatron_merge
Choose a base branch
from
Draft

Conversation

yfw
Copy link
Collaborator

@yfw yfw commented May 21, 2025

What does this PR do ?

This allows us to use NeMo's llm export mapping and transforms when converting megatron params to HF params for refit. The mapping and transforms in nemo_rl/models/megatron/converters/qwen2.py is currently copied from https://github.com/NVIDIA/NeMo/blob/c882b4885349b5a750147d242338ebcbc7058ef6/nemo/collections/llm/gpt/model/qwen2.py#L316-L358

Issues

List issues that this PR closes (syntax):

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:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
  • Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

  • ...

yfw added 4 commits May 21, 2025 15:06
Signed-off-by: Yi-Fu Wu <yifu.wu@gmail.com>
Signed-off-by: Yi-Fu Wu <yifu.wu@gmail.com>
Signed-off-by: Yi-Fu Wu <yifu.wu@gmail.com>
Signed-off-by: Yi-Fu Wu <yifu.wu@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant