Skip to content

[WIP]feature(mixtral): support Mixtral-8x7B SFT, Reward, and Alignment #95

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 33 commits into
base: main
Choose a base branch
from
Open

[WIP]feature(mixtral): support Mixtral-8x7B SFT, Reward, and Alignment #95

wants to merge 33 commits into from

Conversation

@haolin-nju
Copy link
Collaborator

@haolin-nju haolin-nju commented Sep 24, 2024

This PR involves:

  1. Support Mixture-of-Experts model and Expert Parallel (EP) in ChatLearn;
  2. Implement an example on Mixtral-8x7B SFT, Reward, RLHF, DPO, and other alignment algorithms.

@haolin-nju haolin-nju changed the title [WIP] Feature: Support Mixtral-8x7B SFT, Reward, Alignment [WIP] Feature: Support Mixtral-8x7B SFT, Reward, and Alignment Sep 24, 2024
@haolin-nju haolin-nju changed the title [WIP] Feature: Support Mixtral-8x7B SFT, Reward, and Alignment [WIP][feature] Support Mixtral-8x7B SFT, Reward, and Alignment Oct 22, 2024
loofahcus
loofahcus reviewed Oct 23, 2024
View reviewed changes
examples/megatron/scripts/train_sft_mixtral.sh Outdated
NNODES=$WORLD_SIZE


dp=$(($WORLD_SIZE * $GPUS_PER_NODE / $tp / $pp / $ep))
Copy link

@loofahcus loofahcus Oct 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it's not supposed to divide ep here.

Copy link
Collaborator Author

@haolin-nju haolin-nju Nov 7, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

loofahcus
loofahcus reviewed Oct 23, 2024
View reviewed changes
examples/megatron/scripts/train_reward_mixtral.sh Outdated
NNODES=$WORLD_SIZE


dp=$(($WORLD_SIZE * $GPUS_PER_NODE / $tp / $pp / $ep))
Copy link

@loofahcus loofahcus Oct 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

neither is here.

Copy link
Collaborator Author

@haolin-nju haolin-nju Nov 7, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

loofahcus
loofahcus reviewed Oct 23, 2024
View reviewed changes
examples/megatron/scripts/train_reward_mixtral.sh Outdated
cd ${CHATLEARN}/examples/megatron/alignment/reward

torchrun $DISTRIBUTED_ARGS \
finetune_reward.py \
Copy link

@loofahcus loofahcus Oct 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should be entry/train_reward.py

Copy link
Collaborator Author

@haolin-nju haolin-nju Nov 7, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

loofahcus
loofahcus reviewed Oct 23, 2024
View reviewed changes
examples/megatron/scripts/train_sft_mixtral.sh Outdated
cd ${CHATLEARN}/examples/megatron/sft

torchrun $DISTRIBUTED_ARGS \
finetune_sft.py \
Copy link

@loofahcus loofahcus Oct 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

shold be entry/train_sft.py

Copy link
Collaborator Author

@haolin-nju haolin-nju Nov 7, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

@haolin-nju haolin-nju mentioned this pull request Dec 5, 2024
Closed
@haolin-nju haolin-nju changed the title [WIP][feature] Support Mixtral-8x7B SFT, Reward, and Alignment [WIP]feature(mixtral): support Mixtral-8x7B SFT, Reward, and Alignment Jan 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

1 more reviewer

@loofahcus loofahcus loofahcus left review comments

Reviewers whose approvals may not affect merge requirements

At least 2 approving reviews are required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@haolin-nju @loofahcus