mzguntalan / zephyrLinks
Zephyr is a declarative neural network library on top of JAX allowing for easy and fast neural network designing, creation, and manipulation
☆36Updated 4 months ago
Alternatives and similar repositories for zephyr
Users that are interested in zephyr are comparing it to the libraries listed below
Sorting:
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆107Updated 2 months ago
- An implementation of AlphaZero and MCTS with neural networks for Tetris☆22Updated 10 months ago
- A pure and fast NumPy implementation of Mamba with cache support.☆17Updated last year
- Schedule free optimiser implemented in JAX using Optimistix☆15Updated last year
- 🧱 Modula software package☆322Updated 5 months ago
- Minimal JAX implementation unifying Diffusion and Flow Matching algorithms as alternative strategies for transporting data distributions.☆63Updated last month
- ☆27Updated last year
- A flexible and extensible reinforcement learning library for Python, designed for both beginners and researchers.☆18Updated last year
- Cellular Automata Accelerated in JAX (Oral at ICLR 2025)☆239Updated 2 months ago
- Flexible Inference for Predictive Coding Networks in JAX.☆65Updated 2 weeks ago
- Cost aware hyperparameter tuning algorithm☆177Updated last year
- Code for the Fractured Entangled Representation Hypothesis position paper!☆221Updated 2 months ago
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆73Updated last year
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆105Updated last year
- SIMD quantization kernels☆94Updated 4 months ago
- Jax/Flax rewrite of Karpathy's nanoGPT☆63Updated 2 years ago
- A compositional diagramming and animation library as an eDSL in Python☆217Updated last year
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆286Updated last year
- fast + parallel AlphaZero in JAX☆109Updated last year
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆71Updated 8 months ago
- This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"☆288Updated 2 months ago
- Simple Transformer in Jax☆142Updated last year
- Attention Kernels for Symmetric Power Transformers☆128Updated 4 months ago
- ☆214Updated 3 weeks ago
- ☆45Updated 2 months ago
- An Open-Ended Agentic Simulator☆58Updated last year
- Automated Capability Discovery via Foundation Model Self-Exploration☆66Updated 11 months ago
- Gradient descent is cool and all, but what if we could delete it?☆106Updated 5 months ago
- Reinforcement learning with Equinox☆20Updated 10 months ago
- Evaluating the Mamba architecture on the Othello game☆49Updated last year