vvvm23 / mezo-jaxLinks
JAX implementation of "Fine-Tuning Language Models with Just Forward Passes"
☆19Updated 2 years ago
Alternatives and similar repositories for mezo-jax
Users that are interested in mezo-jax are comparing it to the libraries listed below
Sorting:
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- ☆52Updated last year
- ☆33Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆39Updated 2 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆89Updated last year
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- A centralized place for deep thinking code and experiments☆86Updated 2 years ago
- ☆51Updated last year
- ☆53Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆63Updated 4 years ago
- Code for the paper "Function-Space Learning Rates"☆23Updated 4 months ago
- Deep Networks Grok All the Time and Here is Why☆37Updated last year
- ICML 2022: Learning Iterative Reasoning through Energy Minimization☆48Updated 2 years ago
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efficient, non-parametric inf…☆25Updated 11 months ago
- ☆45Updated last year
- The Energy Transformer block, in JAX☆59Updated last year
- ☆31Updated 6 months ago
- train with kittens!☆62Updated 11 months ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- Experiment of using Tangent to autodiff triton☆81Updated last year
- Code for minimum-entropy coupling.☆32Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆58Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆81Updated 2 years ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated last year
- Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (…☆23Updated 3 months ago
- Code implementing "Efficient Parallelization of a Ubiquitious Sequential Computation" (Heinsen, 2023)☆93Updated 10 months ago
- ☆34Updated last year
- NF-Layers for constructing neural functionals.☆89Updated last year
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆12Updated 2 years ago