[Non-Record] LegendreGPT: Legendre polynomial depth parameterization#1337
Merged
valerio-oai merged 5 commits intoopenai:mainfrom May 3, 2026
Merged
[Non-Record] LegendreGPT: Legendre polynomial depth parameterization#1337valerio-oai merged 5 commits intoopenai:mainfrom
valerio-oai merged 5 commits intoopenai:mainfrom
Conversation
valerio-oai
approved these changes
May 3, 2026
Contributor
valerio-oai
left a comment
valerio-oai
left a comment
There was a problem hiding this comment.
Selected for the notable non-record submissions section.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Non-record submission (1x RTX 5090, ~27h training).
Pre-quant val_bpb: 1.2079
Post-quant val_bpb: 1.2266 (mixed INT8/INT7+LZMA, 15.70 MB)
Transformer weights parameterized as smooth functions of depth via Legendre polynomials. 2-group architecture with 24 virtual layers from 12 coefficient matrices.