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!)
☆1,253Updated 3 months ago
Alternatives and similar repositories for hlb-CIFAR10:
Users that are interested in hlb-CIFAR10 are comparing it to the libraries listed below
- Cramming the training of a (BERT-type) language model into limited compute.☆1,326Updated 9 months ago
- Tensors, for human consumption☆1,208Updated 4 months ago
- What would you do with 1000 H100s...☆1,029Updated last year
- maximal update parametrization (µP)☆1,492Updated 8 months ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,117Updated 4 months ago
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆956Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆374Updated this week
- TensorDict is a pytorch dedicated tensor container.☆905Updated this week
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.☆727Updated 11 months ago
- Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/☆1,359Updated last week
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆477Updated 2 years ago
- Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation☆1,469Updated last year
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,001Updated 7 months ago
- ☆528Updated last year
- For optimization algorithm research and development.☆504Updated this week
- Schedule-Free Optimization in PyTorch☆2,129Updated 2 weeks ago
- Language Modeling with the H3 State Space Model☆519Updated last year
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,749Updated 3 months ago
- Puzzles for exploring transformers☆336Updated last year
- Convolutions for Sequence Modeling☆878Updated 9 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…☆342Updated 8 months ago
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆381Updated 10 months ago
- Notebooks and various random fun☆1,093Updated last year
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆456Updated last year
- Named tensors with first-class dimensions for PyTorch☆319Updated last year
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆629Updated last year
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆633Updated last year
- ☆425Updated 5 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…☆1,560Updated last year