cgarciae / dyn_plotLinks
☆13Updated last year
Alternatives and similar repositories for dyn_plot
Users that are interested in dyn_plot are comparing it to the libraries listed below
Sorting:
- ☆60Updated 3 years ago
- ☆44Updated last month
- A functional training loops library for JAX☆88Updated last year
- Code for the paper "Function-Space Learning Rates"☆23Updated 6 months ago
- Recursive Leasting Squares (RLS) with Neural Network for fast learning☆57Updated 2 years ago
- Maximal Update Parametrization (μP) with Flax & Optax.☆16Updated last year
- If it quacks like a tensor...☆59Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆92Updated last year
- Train vision models using JAX and 🤗 transformers☆100Updated last month
- minGPT in JAX☆48Updated 3 years ago
- ☆24Updated 11 months ago
- JAX/Flax implementation of the Hyena Hierarchy☆34Updated 2 years ago
- Einsum-like high-level array sharding API for JAX☆34Updated last year
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- Implementations of growing and pruning in neural networks☆22Updated 2 years ago
- LoRA for arbitrary JAX models and functions☆143Updated last year
- Gradient-based constrained optimization for JAX☆37Updated 3 years ago
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆47Updated last year
- Running Jax in PyTorch Lightning☆115Updated 11 months ago
- Open source code for EigenGame.☆33Updated 2 years ago
- ☆35Updated last year
- ☆62Updated last year
- Neural Networks for JAX☆84Updated last year
- nanoGPT using Equinox☆14Updated 2 years ago
- Code for minimum-entropy coupling.☆32Updated 2 weeks ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆38Updated 3 years ago
- This is a port of Mistral-7B model in JAX☆32Updated last year
- ☆118Updated last month
- Pytorch implementation of SuperPolyak subgradient method.☆43Updated 3 years ago
- A port of muP to JAX/Haiku☆25Updated 3 years ago