NTT123 / pax
A stateful pytree library for training neural networks.
☆21Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for pax
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆30Updated last year
- A GPT, made only of MLPs, in Jax☆55Updated 3 years ago
- ☆29Updated 3 weeks ago
- ☆62Updated 3 months ago
- Image augmentation library for Jax☆37Updated 7 months ago
- HomebrewNLP in JAX flavour for maintable TPU-Training☆46Updated 10 months ago
- A home for audio ML in JAX. Has common features, learnable frontends, pretrained supervised and self-supervised models.☆62Updated 2 years ago
- AdaCat☆49Updated 2 years ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆38Updated 2 years ago
- ☆18Updated 7 months ago
- ☆38Updated last year
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆45Updated 2 years ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆42Updated 5 months ago
- Local Attention - Flax module for Jax☆20Updated 3 years ago
- minGPT in JAX☆46Updated 2 years ago
- RWKV model implementation☆38Updated last year
- This repository contains example code to build models on TPUs☆30Updated last year
- ☆99Updated 4 months ago
- A simple Transformer where the softmax has been replaced with normalization☆18Updated 4 years ago
- [ICML 2024] SIRFShampoo: Structured inverse- and root-free Shampoo in PyTorch (https://arxiv.org/abs/2402.03496)☆13Updated 2 weeks ago
- ☆16Updated 2 months ago
- ☆58Updated 2 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago