Skip to content

Derive msa_subsample_at_inference from nullable msa_max_depth#343

Merged
faustomilletari merged 1 commit into
mainfrom
fm/esmfold2-msa-knobs-local-1
Jun 11, 2026
Merged

Derive msa_subsample_at_inference from nullable msa_max_depth#343
faustomilletari merged 1 commit into
mainfrom
fm/esmfold2-msa-knobs-local-1

Conversation

@faustomilletari

Copy link
Copy Markdown
Collaborator

Make msa_max_depth nullable (int | None) in the local fold(), matching the forge FoldingConfig surface. The model's msa_subsample_at_inference kwarg is no longer exposed directly; instead it's derived: None depth => use the full MSA (no subsampling), otherwise subsample. The transformers model is unchanged (it already no-ops when max_depth is None or subsampling is disabled).

Make msa_max_depth nullable (int | None) in the local fold(), matching
the forge FoldingConfig surface. The model's msa_subsample_at_inference
kwarg is no longer exposed directly; instead it's derived: None depth
=> use the full MSA (no subsampling), otherwise subsample. The
transformers model is unchanged (it already no-ops when max_depth is
None or subsampling is disabled).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@github-actions

github-actions Bot commented Jun 9, 2026

Copy link
Copy Markdown
Tests Skipped Failures Errors Time
28 1 💤 0 ❌ 0 🔥 17.856s ⏱️

@faustomilletari faustomilletari merged commit d96737e into main Jun 11, 2026
5 checks passed
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