facebookresearch / projUNN

Related projects ⓘ

Alternatives and complementary repositories for projUNN

• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years ago
• gregorbachmann / scaling_mlps
  ☆51Updated 5 months ago
• shikaiqiu / compute-better-spent
  ☆46Updated last month
• lucidrains / autoregressive-linear-attention-cuda
  CUDA implementation of autoregressive linear attention, with all the latest research findings
  ☆43Updated last year
• ClashLuke / tpucare
  Automatically take good care of your preemptible TPUs
  ☆32Updated last year
• peerdavid / layerwise-batch-entropy
  Layerwise Batch Entropy Regularization
  ☆22Updated 2 years ago
• vvvm23 / mezo-jax
  JAX implementation of "Fine-Tuning Language Models with Just Forward Passes"
  ☆20Updated last year
• aks2203 / deep-thinking
  A centralized place for deep thinking code and experiments
  ☆77Updated last year
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆53Updated 11 months ago
• AndPotap / einsum-search
  ☆25Updated last month
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆52Updated last month
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆79Updated 9 months ago
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆34Updated last year
• SamsungSAILMontreal / ghn3
  Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]
  ☆31Updated 2 months ago
• facebookresearch / LAWT
  Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)
  ☆64Updated 3 months ago
• ermongroup / fast_feedforward_computation
  Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021
  ☆26Updated 3 years ago
• f-dangel / singd
  [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)
  ☆20Updated 2 weeks ago
• IDSIA / recurrent-fwp
  Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)
  ☆47Updated last year
• matthias-wright / jax-fid
  FID computation in Jax/Flax.
  ☆24Updated 4 months ago
• google-research / precondition
  ☆29Updated 3 weeks ago
• sjunhongshen / DASH
  ☆21Updated last year
• ludwigwinkler / JaxLightning
  Running Jax in PyTorch Lightning
  ☆82Updated 2 weeks ago
• srush / mamba-scans
  Blog post
  ☆16Updated 9 months ago
• lucidrains / einops-exts
  Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️
  ☆52Updated last year
• davisyoshida / qax
  If it quacks like a tensor...
  ☆52Updated last week
• ganguli-lab / degrees-of-freedom
  ☆36Updated 2 years ago
• EkdeepSLubana / MMC
  Codebase for Mechanistic Mode Connectivity
  ☆13Updated last year
• ahennequ / pytorch-custom-mma
  ☆29Updated 2 years ago