lucas-maes / nano-simsiamLinks
Minimalistic, hackable PyTorch implementation of SimSiam in ~400 lines. Achieves good performance on ImageNet with ResNet50. Features distributed training, real-time KNN eval, and AMP. Perfect for research prototyping.
☆21Updated last year
Alternatives and similar repositories for nano-simsiam
Users that are interested in nano-simsiam are comparing it to the libraries listed below
Sorting:
- ☆40Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆188Updated last week
- ☆35Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆92Updated last year
- JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)☆40Updated last year
- ☆62Updated last year
- Jax/Flax rewrite of Karpathy's nanoGPT☆62Updated 2 years ago
- A simple library for scaling up JAX programs☆144Updated last month
- Implementation of PSGD optimizer in JAX☆35Updated 11 months ago
- Pytorch-like dataloaders for JAX.☆98Updated 6 months ago
- Parallel Associative Scan for Language Models☆18Updated last year
- Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).☆117Updated 3 years ago
- Tensor Parallelism with JAX + Shard Map☆11Updated 2 years ago
- ☆17Updated last year
- Parallelizing non-linear sequential models over the sequence length☆56Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆37Updated 2 years ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated 2 years ago
- ☆34Updated last year
- An implementation of the Llama architecture, to instruct and delight☆21Updated 6 months ago
- A functional training loops library for JAX☆88Updated last year
- Running Jax in PyTorch Lightning☆115Updated 11 months ago
- Code for the paper "Function-Space Learning Rates"☆23Updated 6 months ago
- Scaling scaling laws with board games.☆54Updated 2 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆77Updated last year
- JMP is a Mixed Precision library for JAX.☆211Updated 10 months ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆38Updated 3 years ago
- ☆121Updated 6 months ago
- Simple tools to mix and match PyTorch and Jax - Get the best of both worlds!☆36Updated last month
- ☆33Updated last year
- ☆50Updated 5 years ago