NTT123 / paxLinks
A stateful pytree library for training neural networks.
☆22Updated 2 months ago
Alternatives and similar repositories for pax
Users that are interested in pax are comparing it to the libraries listed below
Sorting:
- Image augmentation library for Jax☆40Updated last year
- A GPT, made only of MLPs, in Jax☆58Updated 4 years ago
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆47Updated last year
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆32Updated 2 years ago
- A selection of neural network models ported from torchvision for JAX & Flax.☆44Updated 3 months ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆39Updated 3 years ago
- AdaCat☆49Updated 3 years ago
- ☆40Updated 2 years ago
- HomebrewNLP in JAX flavour for maintable TPU-Training☆51Updated last year
- A home for audio ML in JAX. Has common features, learnable frontends, pretrained supervised and self-supervised models.☆69Updated 3 years ago
- ☆107Updated last year
- ☆26Updated 3 years ago
- ☆60Updated 3 years ago
- Python Research Framework☆106Updated 3 years ago
- A functional training loops library for JAX☆88Updated last year
- ☆21Updated 2 years ago
- Very deep VAEs in JAX/Flax☆46Updated 4 years ago
- ☆33Updated 2 years ago
- Amos optimizer with JEstimator lib.☆82Updated last year
- A generative modelling toolkit for PyTorch.☆70Updated 4 years ago
- ☆31Updated this week
- Latent Diffusion Language Models☆69Updated 2 years ago
- ☆24Updated 6 years ago
- A framework for implementing equivariant DL☆10Updated 4 years ago
- Local Attention - Flax module for Jax☆22Updated 4 years ago
- ☆62Updated 3 years ago
- minGPT in JAX☆48Updated 3 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆188Updated 3 years ago
- Flax (JAX) implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation☆12Updated 4 years ago
- ☆33Updated 4 years ago