konstantinosKokos / apeLinks
๐งฎ Algebraic Positional Encodings.
โ16Updated last month
Alternatives and similar repositories for ape
Users that are interested in ape are comparing it to the libraries listed below
Sorting:
- The Energy Transformer block, in JAXโ59Updated last year
- โ32Updated 11 months ago
- โ31Updated 5 months ago
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inferenceโ16Updated 7 months ago
- Meta-learning inductive biases in the form of useful conserved quantities.โ37Updated 2 years ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.โ41Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)โ32Updated last year
- Simple Scalable Discrete Diffusion for text in PyTorchโ36Updated 11 months ago
- Source code for the paper "Positional Attention: Expressivity and Learnability of Algorithmic Computation"โ14Updated 3 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paperโ59Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023โ20Updated 2 years ago
- Scalable and Stable Parallelization of Nonlinear RNNSโ22Updated 3 weeks ago
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwoโฆโ72Updated 2 months ago
- RWKV model implementationโ38Updated 2 years ago
- โ57Updated 11 months ago
- โ13Updated 3 months ago
- An annotated implementation of the Hyena Hierarchy paperโ33Updated 2 years ago
- โ22Updated 3 years ago
- Fast singularity detection with kernelโ37Updated last year
- Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"โ84Updated 2 years ago
- Repository for Sparse Universal Transformersโ19Updated last year
- โ52Updated last year
- Graphically structured diffusion model.โ20Updated 2 years ago
- How to Turn Your Knowledge Graph Embeddings into Generative Modelsโ53Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAXโ88Updated last year
- JAX/Flax implementation of the Hyena Hierarchyโ34Updated 2 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"โ59Updated 3 years ago
- Parallelizing non-linear sequential models over the sequence lengthโ54Updated 2 months ago
- Implementation of deep implicit attention in PyTorchโ65Updated 4 years ago
- โ38Updated 3 years ago