10L Int5-MLP + BigramHash(4096) + SWA (1.1507 BPB)#694
Open
Bortlesboat wants to merge 2 commits intoopenai:mainfrom
Open
10L Int5-MLP + BigramHash(4096) + SWA (1.1507 BPB)#694Bortlesboat wants to merge 2 commits intoopenai:mainfrom
Bortlesboat wants to merge 2 commits intoopenai:mainfrom
Conversation
Explores stacking eval-time techniques (neural cache, LoRA TTT) and quantization-aware training on top of the openai#1 recipe. QAT has an export mismatch bug resulting in high quantization penalty — submitting as non-record to document the approach for iteration.
Non-record submission. 10 layers, d=512, GQA 8H/4KV, mixed int5/int6 quantization + zstd-22. BigramHash(4096, dim=128), SmearGate, SWA(0.4). Mean of 3 seeds: 1.1507 +/- 0.0006 BPB. All artifacts under 16MB.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Non-record submission
val_bpb: 1.1507 (mean of 3 seeds, sliding window stride=64, post int5/int6+zstd quantization roundtrip)
Architecture
Based on
thwu1's 10L Int5-MLP submission with reduced BigramHash for reliable size margin across seeds.
Timing (8xH100 SXM)