KellerJordan / cifar10-airbenchLinks
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
β251Updated 3 months ago
Alternatives and similar repositories for cifar10-airbench
Users that are interested in cifar10-airbench are comparing it to the libraries listed below
Sorting:
- π§± Modula software packageβ200Updated 2 months ago
- Efficient optimizersβ220Updated this week
- β270Updated 11 months ago
- Normalized Transformer (nGPT)β183Updated 7 months ago
- Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"β108Updated 2 months ago
- β188Updated 6 months ago
- supporting pytorch FSDP for optimizersβ82Updated 6 months ago
- Accelerated First Order Parallel Associative Scanβ182Updated 10 months ago
- A library for unit scaling in PyTorchβ125Updated 6 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β134Updated this week
- Universal Tensor Operations in Einstein-Inspired Notation for Python.β382Updated 2 months ago
- Understand and test language model architectures on synthetic tasks.β217Updated 2 weeks ago
- DeMo: Decoupled Momentum Optimizationβ188Updated 6 months ago
- WIPβ93Updated 10 months ago
- The AdEMAMix Optimizer: Better, Faster, Older.β183Updated 9 months ago
- Annotated version of the Mamba paperβ485Updated last year
- Implementation of Diffusion Transformer (DiT) in JAXβ278Updated last year
- A MAD laboratory to improve AI architecture designs π§ͺβ120Updated 6 months ago
- When it comes to optimizers, it's always better to be safe than sorryβ241Updated 2 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).β272Updated last week
- For optimization algorithm research and development.β521Updated this week
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"β235Updated 2 weeks ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Ruleβ173Updated 3 months ago
- β53Updated 8 months ago
- Getting crystal-like representations with harmonic lossβ189Updated 2 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ284Updated 2 weeks ago
- β78Updated 11 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditionβ¦β177Updated last week
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Coresβ319Updated 5 months ago
- β286Updated last month