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

Add MPT-7B-instruct HuggingFace Model #1773

Closed
wants to merge 3 commits into from

Conversation

apsonawane
Copy link
Contributor

PR to add https://huggingface.co/mosaicml/mpt-7b-instruct in torchbenchmark.
Running mpt-7b-instruct requires trust_remote_code to be passed

@apsonawane apsonawane force-pushed the asonawane/mpt branch 3 times, most recently from a1545f9 to 204dc04 Compare July 20, 2023 18:13
@apsonawane
Copy link
Contributor Author

Rebased with recent changes no merge conflicts

@msaroufim
Copy link
Member

msaroufim commented Aug 1, 2023

You're still getting an upstream error from a broken PR (which I made earlier so my bad) - you can try rebasing or something easier is since we don't care about history since everything is getting squashed on merge anws


git checkout main
git pull
git checkout your_branch
git merge main
# fix merge conflicts
git push

@xuzhao9
Copy link
Contributor

xuzhao9 commented Aug 2, 2023

Could you please rebase this on the latest main branch, and push it again?

@apsonawane
Copy link
Contributor Author

Updated the branch and pushed

@xuzhao9
Copy link
Contributor

xuzhao9 commented Aug 3, 2023

@apsonawane Sorry can you help resolve the conflicts?

@facebook-github-bot
Copy link
Contributor

@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

Copy link
Contributor

@xuzhao9 xuzhao9 left a comment

Choose a reason for hiding this comment

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

LGTM

torchbenchmark/models/hf_MPT_7b_instruct/metadata.yaml Outdated Show resolved Hide resolved
@facebook-github-bot
Copy link
Contributor

@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

DEFAULT_TRAIN_BSIZE = 4
DEFAULT_EVAL_BSIZE = 1

def __init__(self, test, device, jit=False, batch_size=None, extra_args=[]):
Copy link
Contributor

Choose a reason for hiding this comment

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

Similarly, can you remove the jit=False argument and the jit=jit argument below? Sorry I missed this in my previous review.

@facebook-github-bot
Copy link
Contributor

@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

DEFAULT_EVAL_BSIZE = 1

def __init__(self, test, device, batch_size=None, extra_args=[]):
super().__init__(name="hf_MPT_7b_instruct", test=test, device=device, jit=jit, batch_size=batch_size, extra_args=extra_args)
Copy link
Contributor

Choose a reason for hiding this comment

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

Could you please also remove the jit=jit argument here? @apsonawane

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Oh my bad. Sorry I am missing these things

Copy link
Contributor

Choose a reason for hiding this comment

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

No worries!

@facebook-github-bot
Copy link
Contributor

@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link
Contributor

@xuzhao9 merged this pull request in 0b7147f.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants