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

extract inference weights #6353

Merged
merged 7 commits into from
Apr 5, 2023
Merged

extract inference weights #6353

merged 7 commits into from
Apr 5, 2023

Conversation

arendu
Copy link
Collaborator

@arendu arendu commented Apr 3, 2023

What does this PR do ?

Adds a script to extract p_tuned inference weights.

More details: The ptuning training saves all params including the prompt encoder weights. These are typically not required after training is completed. The script allows you to save the required representations for inference in a separate file and you can delete the .nemo if wanted.

Collection: [Note which collection this PR will affect]

Changelog

  • Add specific line by line info of 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:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?
  • Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
    • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

  • New Feature
  • Bugfix
  • Documentation

If you haven't finished some of the above items you can still open "Draft" PR.

Who can review?

Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.

Additional Information

  • Related to # (issue)

@arendu arendu requested a review from Zhilin123 April 3, 2023 20:20
try:
a = torch.load(f'{p}model_weights.ckpt')
break
except FileNotFoundError:

Check notice

Code scanning / CodeQL

Empty except

'except' clause does nothing but pass and there is no explanatory comment.
Zhilin123
Zhilin123 previously approved these changes Apr 3, 2023
Copy link
Collaborator

@Zhilin123 Zhilin123 left a comment

Choose a reason for hiding this comment

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

LGTM! Can you comment on the PR what this PR is for ie why we need to extract weights for inference? No code changes needed.

Copy link
Collaborator

@Zhilin123 Zhilin123 left a comment

Choose a reason for hiding this comment

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

LGTM

@arendu arendu merged commit e727916 into main Apr 5, 2023
@arendu arendu deleted the adithyare/extraction branch April 5, 2023 06:02
hsiehjackson pushed a commit to hsiehjackson/NeMo that referenced this pull request Jun 2, 2023
* extract inf weights

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

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* updated

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

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: arendu <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: hsiehjackson <[email protected]>
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.

None yet

2 participants