ruslangrimov / mnist-minimal-modelLinks
Trying to find out what is the minimal model that can achieve 99% accuracy on MNIST dataset
☆25Updated 6 years ago
Alternatives and similar repositories for mnist-minimal-model
Users that are interested in mnist-minimal-model are comparing it to the libraries listed below
Sorting:
- bfloat16 dtype for numpy☆19Updated last year
- Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit☆158Updated last year
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆46Updated last year
- Experiment of using Tangent to autodiff triton☆79Updated last year
- FastFeedForward Networks☆20Updated last year
- Machine Learning Agility (MLAgility) benchmark and benchmarking tools☆39Updated 2 months ago
- Benchmarking PyTorch 2.0 different models☆21Updated 2 years ago
- Hacks for PyTorch☆19Updated 2 years ago
- NNCG: A Neural Network Code Generator☆35Updated 11 months ago
- Samples of good AI generated CUDA kernels☆84Updated last month
- A Data-Centric Compiler for Machine Learning☆84Updated last year
- Butterfly matrix multiplication in PyTorch☆172Updated last year
- ☆52Updated 11 months ago
- A list of awesome neural symbolic papers.☆47Updated 2 years ago
- Supplementary material for our paper "Compute Trends Across Three Eras of Machine Learning".☆40Updated 3 years ago
- Generic floating-point types in Python☆13Updated 3 months ago
- A stand-alone implementation of several NumPy dtype extensions used in machine learning.☆280Updated last week
- Repository of machine learning benchmarks☆39Updated last week
- 🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.☆64Updated 5 months ago
- Fast training of unitary deep network layers from low-rank updates☆28Updated 2 years ago
- Open source version of ArchGym project.☆117Updated 3 months ago
- Explore training for quantized models☆20Updated this week
- E2E AutoML Model Compression Package☆46Updated 4 months ago
- Customized matrix multiplication kernels☆56Updated 3 years ago
- A Deep Learning Framework for the Posit Number System☆29Updated 11 months ago
- [JMLR'20] NeurIPS 2019 MicroNet Challenge Efficient Language Modeling, Champion☆40Updated 4 years ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆70Updated last year
- ☆28Updated 6 months ago
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆45Updated last year
- ☆18Updated last year