-
Notifications
You must be signed in to change notification settings - Fork 280
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
Conversation
c64b24d
to
59e6c21
Compare
a1545f9
to
204dc04
Compare
204dc04
to
7d3f086
Compare
Rebased with recent changes no merge conflicts |
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
|
Could you please rebase this on the latest main branch, and push it again? |
Updated the branch and pushed |
@apsonawane Sorry can you help resolve the conflicts? |
@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
5db3651
to
dc65d8c
Compare
@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=[]): |
There was a problem hiding this comment.
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.
dc65d8c
to
3973b97
Compare
@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) |
There was a problem hiding this comment.
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
There was a problem hiding this comment.
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
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No worries!
3973b97
to
ee75280
Compare
@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
PR to add https://huggingface.co/mosaicml/mpt-7b-instruct in torchbenchmark.
Running mpt-7b-instruct requires
trust_remote_code
to be passed