mzguntalan / zephyr
Zephyr is a declarative neural network library on top of JAX allowing for easy and fast neural network designing, creation, and manipulation
☆23Updated this week
Related projects ⓘ
Alternatives and complementary repositories for zephyr
- Schedule free optimiser implemented in JAX using Optimistix☆14Updated 5 months ago
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code☆26Updated 2 months ago
- A pure and fast NumPy implementation of Mamba with cache support.☆17Updated 4 months ago
- ☆27Updated 4 months ago
- Gpu benchmark☆43Updated last month
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆84Updated 2 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated last month
- OMNI: Open-endedness via Models of human Notions of Interestingness☆37Updated 10 months ago
- Scalable neural net training via automatic normalization in the modular norm.☆119Updated 2 months ago
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning☆50Updated 3 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆45Updated 5 months ago
- ☆17Updated 4 months ago
- fast + parallel AlphaZero in JAX☆84Updated 7 months ago
- ☆29Updated last month
- [ICML 2024] Official code release accompanying the paper "diff History for Neural Language Agents" (Piterbarg, Pinto, Fergus)☆18Updated 2 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆84Updated last month
- ☆64Updated last week
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆31Updated last month
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselin…☆40Updated this week
- ☆62Updated 2 months ago
- Jax like function transformation engine but micro, microjax☆26Updated 2 weeks ago
- A high throughput, end-to-end RL library for infinite horizon tasks.☆18Updated 5 months ago
- coloring terminal text with intensities (used for plotting probability, entropy with tokens)☆12Updated last month
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆87Updated 11 months ago
- ☆58Updated 2 years ago
- Mobile Viewer for W&B, built on top of Flutter.☆30Updated 8 months ago
- Extensive introductory writeup on Zig language functionalities☆10Updated 3 months ago
- Efficient optimizers☆58Updated this week
- Implementation of Soft Actor Critic and some of its improvements in Pytorch☆38Updated 3 weeks ago
- ☆13Updated 3 weeks ago