tysam-code / hlb-CIFAR10Links
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
☆1,262Updated 5 months ago
Alternatives and similar repositories for hlb-CIFAR10
Users that are interested in hlb-CIFAR10 are comparing it to the libraries listed below
Sorting:
- Cramming the training of a (BERT-type) language model into limited compute.☆1,332Updated 11 months ago
- Tensors, for human consumption☆1,252Updated last week
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆958Updated last year
- Notebooks and various random fun☆1,094Updated 2 years ago
- Schedule-Free Optimization in PyTorch☆2,162Updated last week
- Puzzles for exploring transformers☆347Updated 2 years ago
- What would you do with 1000 H100s...☆1,048Updated last year
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆636Updated last year
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,780Updated last month
- ☆775Updated last month
- 🤖 A PyTorch library of curated Transformer models and their composable components☆888Updated last year
- Convolutions for Sequence Modeling☆883Updated 11 months ago
- TensorDict is a pytorch dedicated tensor container.☆925Updated this week
- For optimization algorithm research and development.☆518Updated this week
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆460Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆381Updated this week
- Language Modeling with the H3 State Space Model☆518Updated last year
- maximal update parametrization (µP)☆1,526Updated 10 months ago
- ☆533Updated last year
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,930Updated 11 months ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,640Updated 2 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,004Updated 9 months ago
- Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.☆586Updated 2 months ago
- UNet diffusion model in pure CUDA☆605Updated 11 months ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆479Updated 2 years ago
- ML Collections is a library of Python Collections designed for ML use cases.☆955Updated last month
- Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory☆438Updated 9 months ago
- A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many different…☆287Updated 5 months ago
- Solve puzzles. Improve your pytorch.☆3,569Updated 10 months ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 10 months ago