Track: dev · Level: stretch · Effort: ~10h · Depends on: Write access
Why this matters
Today analyze targets torchvision-style CNNs. A huge share of modern practitioners use Hugging Face transformers, and the common objection to BNNR is that it is 'just demo CNNs'. Making analyze work on a real ViT removes that objection and opens BNNR to a much larger audience, which is a direct path toward standard status.
Steps
- Study how existing adapters work (src/bnnr/adapter.py) and how analyze consumes a model and its target layer.
- Spike: load a transformers ViT and produce one saliency map through BNNR (a ViT exposes attention differently from a CNN, so identify the right target).
- Write a short design note describing the adapter and any limitations, for maintainer review.
Done when
A design note approved by the maintainer and a spike that produces a saliency map from a ViT.
How to take this: comment "taking this" and wait to be assigned. Branch t40-short-desc from upstream/main, and put Closes #<this issue number> in your PR. Full workflow: the Cohort Handbook (pinned in Discord).
Track: dev · Level: stretch · Effort: ~10h · Depends on: Write access
Why this matters
Today analyze targets torchvision-style CNNs. A huge share of modern practitioners use Hugging Face transformers, and the common objection to BNNR is that it is 'just demo CNNs'. Making analyze work on a real ViT removes that objection and opens BNNR to a much larger audience, which is a direct path toward standard status.
Steps
Done when
A design note approved by the maintainer and a spike that produces a saliency map from a ViT.
How to take this: comment "taking this" and wait to be assigned. Branch
t40-short-descfromupstream/main, and putCloses #<this issue number>in your PR. Full workflow: the Cohort Handbook (pinned in Discord).