Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
- cifar10
- deep-learning
- experimentation
- machine-learning
102,118 visible repositories in the index
1–4 of 4 · Most stars
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
Benchmark for vector databases.
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
Benchmark harness and data: QEMU emulation vs native Buildx nodes for multi-arch container builds.