Skip to content

Draft: anymodel activation scoring#989

Open
danielkorzekwa wants to merge 5 commits intodkorzekwa/anymodel_corefrom
dkorzekwa/anymodel_activation_scoring
Open

Draft: anymodel activation scoring#989
danielkorzekwa wants to merge 5 commits intodkorzekwa/anymodel_corefrom
dkorzekwa/anymodel_activation_scoring

Conversation

@danielkorzekwa
Copy link

What does this PR do?

Merging anymodel acivation scoring into anymodel core - this MR is only for reviewing. Ultimately anymodel acivation scoring should be merged into feature/puzzletron once anymodel core is merged there.

@danielkorzekwa danielkorzekwa requested a review from a team as a code owner March 6, 2026 06:42
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Mar 6, 2026

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

🗂️ Base branches to auto review (3)
  • main
  • release/.*
  • feature/.*

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 8b20b5e6-f254-44cc-a7a0-0b7c10a7e6a3

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch dkorzekwa/anymodel_activation_scoring

Comment @coderabbitai help to get the list of available commands and usage tips.

mprint("Starting pruning activation scoring...")

# The checkpoint manager inside validate_model handles all progress tracking
validate_model(args=cfg.pruning, pipeline_parallel=True)
Copy link
Collaborator

Choose a reason for hiding this comment

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

Why this is removed?

) -> None:
incompatible_keys.missing_keys.clear()
incompatible_keys.unexpected_keys.clear()
class DeciLMDummyBlock(DummyModule):
Copy link
Collaborator

Choose a reason for hiding this comment

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

Are these dummy decilm blocks still used?

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.

2 participants