OLYMPUS: The Agora — Community companion for OpenAI Parameter Golf. Live leaderboard, compliance engine, technique map, funding transparency, compute guide.
-
Updated
May 31, 2026 - Python
#
parameter-golf
Here are 12 public repositories matching this topic...
Beating OpenAI's 8×H100 Parameter Golf baseline (1.2019 vs 1.2244 bpb) on a laptop, under a 16MB limit
machine-learning openai research-project quantization mlx model-compression apple-silicon llm parameter-golf
-
Updated
Jul 21, 2026 - Python
HYDRA · parameter-golf fork — tiny LM ≤16MB / ~10min · ~1.061 BPB verified local · receipts + writeup
-
Updated
Jul 20, 2026 - Python
OpenAI Parameter Golf — SOTA 0.3958 BPB (3-seed mean). Beat prior best (0.4416) by 0.0458. Causal BackoffNgramMixer. PR #1094.
-
Updated
Apr 23, 2026 - Python
Parameter Golf v3: ~1.151 BPB in 16MB — Int6 QAT, BigramHash, SmearGate, SWA, zstd-22
-
Updated
Mar 29, 2026 - Jupyter Notebook
Train the smallest LM you can that fits in 16MB. Best model wins!
-
Updated
Sep 26, 2026 - Python
CPU-only language model optimization under a 16 MB constraint — calibration, Bayesian n-gram experts, test-time training, and compression.
machine-learning pytorch language-models model-compression ml-systems llm test-time-training parameter-golf
-
Updated
Sep 7, 2026 - Python
Exploratory compact LM research branch derived from LUMI-Arch, focused on structure-sensitive generalization under tight model constraints.
-
Updated
Mar 26, 2026
Training LLMs under extreme 16MB memory constraints using custom optimizers in PyTorch. tested on H100 clusters (RunPod) for the 16MB OpenAI Parameter Golf Challenge.
machine-learning optimization cuda pytorch artificial-intelligence nvidia openai muon quantization rbf-network pytorch-implementation quantization-algorithms runpod llms h100 parameter-golf
-
Updated
Sep 18, 2026
A practical starter repo and working setup for the OpenAI Parameter Golf competition
-
Updated
Mar 25, 2026 - Python
OpenAI Parameter Golf experiments for parameter-constrained language modeling, ablations, and efficient architecture tradeoffs.
-
Updated
Apr 1, 2026 - Python
Sparse I/O bottleneck language model using C. elegans connectome wiring + JEPA + SigREG. Parameter Golf submission: 1.79 BPB in a 2MB artifact.
-
Updated
Jul 17, 2026 - Python
Add this topic to your repo
To associate your repository with the parameter-golf topic, visit your repo's landing page and select "manage topics."