Skip to content

Fix exact-zero DiffusionGemma self-conditioning - #776

Closed
sylvesterkaczmarek wants to merge 1 commit into
google-deepmind:mainfrom
sylvesterkaczmarek:fix/diffusion-zero-self-conditioning
Closed

Fix exact-zero DiffusionGemma self-conditioning#776
sylvesterkaczmarek wants to merge 1 commit into
google-deepmind:mainfrom
sylvesterkaczmarek:fix/diffusion-zero-self-conditioning

Conversation

@sylvesterkaczmarek

Copy link
Copy Markdown

Address the self-conditioning semantics reported in #773.

Zero vocabulary logits become a nonzero vocabulary-mean embedding after encode_logits, so they cannot represent the report-defined disabled self-conditioning signal. Preserve the existing all-zero-logit sentinel across the embedding boundary and make the no-previous-logits first pass exactly zero as well.

Add regression coverage for the absent signal, the mixed enabled/disabled batch case, and an explicit enable mask.

Address the self-conditioning semantics reported in google-deepmind#773.

Zero vocabulary logits become a nonzero vocabulary-mean embedding after encode_logits, so they cannot represent the report-defined disabled self-conditioning signal. Preserve the existing all-zero-logit sentinel across the embedding boundary and make the no-previous-logits first pass exactly zero as well.

Add regression coverage for the absent signal, the mixed enabled/disabled batch case, and an explicit enable mask.
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.

1 participant