11L AttnRes + Gated Attention + Looped Blocks + EMA + Cosine + QAT#607
Draft
Neopolita wants to merge 1 commit intoopenai:mainfrom
Draft
11L AttnRes + Gated Attention + Looped Blocks + EMA + Cosine + QAT#607Neopolita wants to merge 1 commit intoopenai:mainfrom
Neopolita wants to merge 1 commit intoopenai:mainfrom
Conversation
… Cosine + QAT Architecture: 11 layers, 3x MLP, Block Attention Residuals (replacing skip_weights), per-head gated attention, looped middle blocks (layers 4-7 x2). Training: EMA (0.995), cosine LR decay, QAT (last 15%). 26.5M params, ~13.7MB artifact. H100 run pending.
|
use Flash attention 4 or 3 |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Status
H100 run pending — requesting compute credits. Local M4 Max validation (500 steps): val_bpb 1.475 (float).
Test plan