facebookresearch / projUNNLinks
Fast training of unitary deep network layers from low-rank updates
☆28Updated 2 years ago
Alternatives and similar repositories for projUNN
Users that are interested in projUNN are comparing it to the libraries listed below
Sorting:
- ☆53Updated 8 months ago
- ☆32Updated 8 months ago
- The Energy Transformer block, in JAX☆56Updated last year
- FID computation in Jax/Flax.☆27Updated 10 months ago
- ☆51Updated 11 months ago
- ☆29Updated 6 months ago
- ☆26Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆81Updated last year
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…☆70Updated this week
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆44Updated 10 months ago
- A simple hypernetwork implementation in jax using haiku.☆23Updated 2 years ago
- Experiment of using Tangent to autodiff triton☆79Updated last year
- [TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivative…☆17Updated last year
- JAX implementation of "Fine-Tuning Language Models with Just Forward Passes"☆19Updated last year
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated last week
- Optimization algorithm which fits a ResNet to CIFAR-10 5x faster than SGD / Adam (with terrible generalization)☆14Updated last year
- Official repository for the paper "Zero-Shot AutoML with Pretrained Models"☆47Updated last year
- Deep Networks Grok All the Time and Here is Why☆36Updated last year
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆44Updated 2 years ago
- ☆54Updated 10 months ago
- Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]☆34Updated 9 months ago
- ☆31Updated last month
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 4 years ago
- Fine-grained, dynamic control of neural network topology in JAX.☆21Updated last year
- Differentiable Algorithms and Algorithmic Supervision.☆116Updated last year
- If it quacks like a tensor...☆58Updated 6 months ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆37Updated 2 years ago
- ☆32Updated last year