tysam-code / hlb-CIFAR10
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
☆1,223Updated last year
Related projects ⓘ
Alternatives and complementary repositories for hlb-CIFAR10
- Cramming the training of a (BERT-type) language model into limited compute.☆1,296Updated 5 months ago
- maximal update parametrization (µP)☆1,402Updated 4 months ago
- Tensors, for human consumption☆1,113Updated 3 weeks ago
- ☆751Updated this week
- Schedule-Free Optimization in PyTorch☆1,898Updated 2 weeks ago
- What would you do with 1000 H100s...☆903Updated 10 months ago
- Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation☆1,447Updated last year
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,041Updated 5 months ago
- Convolutions for Sequence Modeling☆869Updated 5 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆970Updated 3 months ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆866Updated 7 months ago
- Notebooks and various random fun☆1,079Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆939Updated 9 months ago
- Puzzles for learning Triton☆1,135Updated this week
- For optimization algorithm research and development.☆449Updated this week
- Language Modeling with the H3 State Space Model☆513Updated last year
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,867Updated 5 months ago
- Puzzles for exploring transformers☆325Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆333Updated 3 weeks ago
- TensorDict is a pytorch dedicated tensor container.☆840Updated this week
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.☆663Updated 6 months ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆471Updated last year
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,679Updated this week
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆604Updated 9 months ago
- ☆391Updated last month
- A platform for managing machine learning experiments☆818Updated 3 months ago
- ML Collections is a library of Python Collections designed for ML use cases.☆896Updated this week
- JAX - A curated list of resources https://github.com/google/jax☆1,562Updated 4 months ago
- ☆508Updated 9 months ago