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

[llama-mm] Onboard Llama3.2 mm vision encoder #6653

Closed
wants to merge 2 commits into from

Conversation

larryliu0820
Copy link
Contributor

@larryliu0820 larryliu0820 commented Nov 5, 2024

Stack from ghstack (oldest at bottom):

Summary: Add llama3.2 mm vision encoder to examples/models.

We need to do a module swapping for TilePositionEmbedding to make sure
vision encoder is exportable.

Test Plan: Unit tests.

Reviewers:

Subscribers:

Tasks:

Tags:

Summary: Add llama3.2 mm vision encoder to examples/models.

We need to do a module swapping for TilePositionEmbedding to make sure
vision encoder is exportable.

Test Plan: Unit tests.

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Nov 5, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6653

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 7 New Failures

As of commit c533944 with merge base 3a1f8d2 (image):

NEW FAILURES - The following jobs have failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

larryliu0820 added a commit that referenced this pull request Nov 5, 2024
Summary: Add llama3.2 mm vision encoder to examples/models.

We need to do a module swapping for TilePositionEmbedding to make sure
vision encoder is exportable.

Test Plan: Unit tests.

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: 4c2a30e6d6b5932a972c34778fea8b3152372e58
Pull Request resolved: #6653
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 5, 2024
Summary: Add llama3.2 mm vision encoder to examples/models.

We need to do a module swapping for TilePositionEmbedding to make sure
vision encoder is exportable.

Test Plan: Unit tests.

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
larryliu0820 added a commit that referenced this pull request Nov 5, 2024
Summary: Add llama3.2 mm vision encoder to examples/models.

We need to do a module swapping for TilePositionEmbedding to make sure
vision encoder is exportable.

Test Plan: Unit tests.

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: f996a614d7ec1b4c7fa4c1cb20bdcc02d813771c
Pull Request resolved: #6653
from executorch.extension.llm.modules._position_embeddings import (
replace_tile_positional_embedding,
)
from torchtune.models.flamingo._component_builders import flamingo_vision_encoder
Copy link
Contributor

Choose a reason for hiding this comment

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

Need to change to:

from torchtune.models.llama3_2_vision._component_builders import llama3_2_vision_encoder

@larryliu0820
Copy link
Contributor Author

Close in favor of #6831

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants