irhum / hyena
JAX/Flax implementation of the Hyena Hierarchy
☆30Updated last year
Related projects ⓘ
Alternatives and complementary repositories for hyena
- An annotated implementation of the Hyena Hierarchy paper☆31Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 5 months ago
- ☆46Updated last month
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆78Updated 9 months ago
- Parallel Associative Scan for Language Models☆18Updated 10 months ago
- Source-to-Source Debuggable Derivatives in Pure Python☆14Updated 9 months ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆86Updated 4 months ago
- ☆25Updated 4 months ago
- Triton Implementation of HyperAttention Algorithm☆46Updated 10 months ago
- Code for minimum-entropy coupling.☆29Updated 4 months ago
- ☆29Updated last month
- Blog post☆16Updated 8 months ago
- Minimum Description Length probing for neural network representations☆16Updated last week
- ☆27Updated 6 months ago
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆16Updated 3 months ago
- ☆24Updated last month
- ☆18Updated last month
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- See https://github.com/cuda-mode/triton-index/ instead!☆11Updated 6 months ago
- ☆31Updated 10 months ago
- My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other h…☆51Updated last year
- Utilities for PyTorch distributed☆23Updated last year
- Automatically take good care of your preemptible TPUs☆31Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆76Updated 2 years ago
- ☆45Updated 9 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated 11 months ago