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!)
☆1,242Updated last month
Alternatives and similar repositories for hlb-CIFAR10:
Users that are interested in hlb-CIFAR10 are comparing it to the libraries listed below
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆945Updated last year
- Tensors, for human consumption☆1,179Updated 2 months ago
- Convolutions for Sequence Modeling☆876Updated 7 months ago
- What would you do with 1000 H100s...☆970Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,311Updated 7 months ago
- Schedule-Free Optimization in PyTorch☆2,069Updated last month
- Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation☆1,456Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆351Updated this week
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,722Updated last month
- Language Modeling with the H3 State Space Model☆515Updated last year
- Notebooks and various random fun☆1,083Updated last year
- ☆760Updated last week
- Puzzles for exploring transformers☆331Updated last year
- maximal update parametrization (µP)☆1,438Updated 6 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆990Updated 5 months ago
- Monte Carlo tree search in JAX☆2,415Updated last month
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆477Updated last year
- ☆413Updated 3 months ago
- For optimization algorithm research and development.☆486Updated last week
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆758Updated last week
- 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…☆279Updated last month
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,087Updated 2 months ago
- arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors …☆1,212Updated last year
- Puzzles for learning Triton☆1,337Updated 2 months ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,405Updated this week
- Code for our NeurIPS 2022 paper☆366Updated 2 years ago
- ☆515Updated 11 months ago
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,550Updated 11 months ago
- UNet diffusion model in pure CUDA☆596Updated 7 months ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆874Updated 9 months ago