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!)
☆1,252Updated 2 months ago
Alternatives and similar repositories for hlb-CIFAR10:
Users that are interested in hlb-CIFAR10 are comparing it to the libraries listed below
- Tensors, for human consumption☆1,192Updated 3 months ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,320Updated 8 months ago
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆949Updated last year
- What would you do with 1000 H100s...☆1,009Updated last year
- A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.☆1,268Updated 7 months ago
- ☆765Updated last month
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆622Updated last year
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,734Updated 2 months ago
- Notebooks and various random fun☆1,090Updated last year
- 🤖 A PyTorch library of curated Transformer models and their composable components☆880Updated 10 months ago
- Puzzles for exploring transformers☆333Updated last year
- Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.☆1,535Updated 2 weeks ago
- maximal update parametrization (µP)☆1,466Updated 7 months ago
- Language Modeling with the H3 State Space Model☆516Updated last year
- Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation☆1,461Updated last year
- 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…☆1,557Updated last year
- Schedule-Free Optimization in PyTorch☆2,105Updated this week
- Convolutions for Sequence Modeling☆876Updated 8 months ago
- ☆418Updated 4 months ago
- Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/☆1,331Updated last week
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,101Updated 3 months ago
- JAX - A curated list of resources https://github.com/google/jax☆1,712Updated last week
- TensorDict is a pytorch dedicated tensor container.☆889Updated this week
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆380Updated 8 months ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,032Updated 10 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…☆281Updated 2 months ago
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.☆702Updated 9 months ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆477Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆342Updated 7 months ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆631Updated last year