Add the Transformer parity test suite#404
Open
LegrandNico wants to merge 1 commit into
Open
Conversation
End-to-end validation of the hybrid GPT against its Equinox twin: the attention backward formula against autodiff, the fully-transplanted frozen model reproducing the reference forward pass (wiring gate), single-step learning parity for the feed-forward swap and the all-PyHGF model, the categorical output head at vocabulary width against softmax backprop, and the 100-step fused trajectory following the backprop twin's cross-entropy curve. Also enforces that categorical layers are leaf-only. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
LegrandNico
force-pushed
the
feat/error-conventions
branch
from
aa62ab2 to
2fa62cc
Compare
LegrandNico
force-pushed
the
feat/transformer-parity
branch
from
fbc682b to
28b81b3
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
End-to-end validation of the hybrid GPT against its Equinox twin: the attention backward formula against autodiff, the fully-transplanted frozen model reproducing the reference forward pass (wiring gate), single-step learning parity for the feed-forward swap and the all-PyHGF model, the categorical output head at vocabulary width against softmax backprop, and the 100-step fused trajectory following the backprop twin's cross-entropy curve. Also enforces that categorical layers are leaf-only.
Stack (7/8) — stacked on #403; next is
deep-networks-docs.🤖 Generated with Claude Code