lucidrains / hyena-dna
Fork of HyenaDNA, a long-range genomic foundation model built with Hyena
☆9Updated last year
Related projects: ⓘ
- Your favourite classical machine learning algos on the GPU/TPU☆20Updated this week
- My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other h…☆51Updated last year
- JAX/Flax implementation of the Hyena Hierarchy☆29Updated last year
- Minimal Implimentation of VCRec (2024) for collapse provention.☆14Updated 5 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆86Updated 3 months ago
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆45Updated last month
- ☆14Updated this week
- Generative cellular automaton-like learning environments for RL.☆19Updated last month
- Clean RL implementation using MLX☆26Updated 6 months ago
- ☆33Updated last year
- ☆23Updated this week
- Toy genetic algorithm in Pytorch☆28Updated 6 months ago
- ☆29Updated this week
- ☆27Updated 2 months ago
- alternative way to calculating self attention☆18Updated 3 months ago
- An annotated implementation of the Hyena Hierarchy paper☆30Updated last year
- Exploration into the Firefly algorithm in Pytorch☆31Updated this week
- Experiments in Joint Embedding Predictive Architectures (JEPAs).☆32Updated 8 months ago
- Implementation of Tranception, an attention network, paired with retrieval, that is SOTA for protein fitness prediction☆31Updated 2 years ago
- gzip Predicts Data-dependent Scaling Laws☆31Updated 3 months ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- Utilities for PyTorch distributed☆23Updated 11 months ago
- This is a port of Mistral-7B model in JAX☆29Updated 2 months ago
- ☆114Updated this week
- Implementation of MambaFormer in Pytorch ++ Zeta from the paper: "Can Mamba Learn How to Learn? A Comparative Study on In-Context Learnin…☆20Updated last week
- A place to store reusable transformer components of my own creation or found on the interwebs☆43Updated 3 weeks ago
- ☆42Updated this week
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆31Updated 3 months ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆40Updated 7 months ago
- RITA is a family of autoregressive protein models, developed by LightOn in collaboration with the OATML group at Oxford and the Debora Ma…☆89Updated last year