-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Pull requests: openai/parameter-golf
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Record: Int6 QAT + SmearGate + Muon WD (val_bpb=1.1669)
#170
opened Mar 20, 2026 by
baudrillardsgh0st
Loading…
5 tasks done
Depth Recurrence via Layer Sharing (3 shared blocks → 1/3 params, matched BPB)
#167
opened Mar 20, 2026 by
SkywardSyntax
Loading…
3 of 5 tasks
Record: Long Context + All Optimizations submission
#166
opened Mar 20, 2026 by
chinesepowered
Loading…
Submission: OrthoInit + Int6 MLP3x + SmearGate + BigramHash (val_bpb: 1.1524)
#164
opened Mar 20, 2026 by
jfprincz
Loading…
SwiGLU dim=576 + Sliding Window + Muon WD (1.2091 BPB)
#163
opened Mar 20, 2026 by
Focus2321
Loading…
Record: Int6 MLP3x + SmearGate + BigramHash + MuonWD + SWA (mean val_bpb=1.1483)
#162
opened Mar 20, 2026 by
raahilshah
Loading…
Record:Add TTT-LoRA 512d submission (val_bpb=1.1957)
#161
opened Mar 20, 2026 by
santosh5541
Loading…
Record: MLP3x + Int8 Tok Emb + Grouped LZMA + Sliding Window (val_bpb=1.1623)
#160
opened Mar 20, 2026 by
ChaseWNorton
Loading…
feat(record): Int6 STE + NorMuon + SWA + Sliding Window (val_bpb=1.16019)
#156
opened Mar 20, 2026 by
dexhunter
Loading…
6 tasks done
Record: sliding eval, FP16 tied embeddings, 10 layers, Muon WD 0.02, overtone init, and phase-transition residual mixing. (val_bpb 1.1876)
#155
opened Mar 20, 2026 by
peytontolbert
Loading…
Non-record: Cross-layer parameter sharing + 4-bit QAT (RecurrentGPT)
#154
opened Mar 20, 2026 by
evnkm
Loading…
Add strong-submission eval pipeline and ablation tooling
#153
opened Mar 20, 2026 by
RogueTex
Loading…
Add TTT (Test-Time Training) submission: 1.1767 BPB
#152
opened Mar 20, 2026 by
timowhite88
Loading…
Non-record: FP16 embed + WD20k + seq2048 + doc-isolated sliding window (val_bpb=1.2045)
#151
opened Mar 20, 2026 by
mrdavtan
Loading…
4 tasks done
Add Combined Int6 + QAT + Sliding Window submission
#149
opened Mar 20, 2026 by
pleasedontddosme
Loading…
Depth Recurrence + Cross-Repeat Skip + Sliding Window Eval
#148
opened Mar 20, 2026 by
iverbovoy
Loading…
Record/smaller batch sota, val_bpb 1.16314679 (post-quant, int6+zlib, sliding eval)
#147
opened Mar 20, 2026 by
ankitmaloo
Loading…
Non-record: Warmdown-Tuned Training (val_bpb=1.2987) on 1xRTX 5090
#146
opened Mar 20, 2026 by
swapp1990
Loading…
3 tasks done
Non-record: QAT ablation — int8 QAT overhead exceeds quantization gap recovery
#145
opened Mar 20, 2026 by
mrdavtan
Loading…
4 tasks done
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.