Fix loading issue in Sam3

[zucchini-nlp]

What does this PR do?

Fix loading in Sam3 which currently doesn't match the state dict keys from checkpoint. Adding a correct base model prefix will add it to all state dict keys, making the ckpt load-able

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[zucchini-nlp]

run-slow: sam3, sam3_video, sam3_tracker_video

[github-actions]

[For maintainers] Suggested jobs to run (before merge)

run-slow: sam3_tracker_video

[github-actions]

Workflow Run ⚙️

This comment contains run-slow, running the specified jobs:

models: ["models/sam3", "models/sam3_tracker_video", "models/sam3_video"]
quantizations: []

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[github-actions]

CI Results

Workflow Run ⚙️

Commit Info

Context	Commit	Description
RUN	a500776c	workflow commit (merge commit)
PR	02dda7d6	branch commit (from PR)
main	aa57e1cd	base commit (on main)

✅ No failing test specific to this PR 🎉 👏 !

[ydshieh]

I know you are busy, but a 1 - 3 sentences to explain what was wrong and the fix etc would be nice.

Always have a bit of context - make the history more accessbible.

Thank you for the fix!!