lucidrains / compositional-attention-pytorch
Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process with disentangled search and retrieval head aggregation, in Pytorch
☆50Updated 2 years ago
Alternatives and similar repositories for compositional-attention-pytorch:
Users that are interested in compositional-attention-pytorch are comparing it to the libraries listed below
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆35Updated 3 years ago
- An open source implementation of CLIP.☆32Updated 2 years ago
- ☆29Updated 2 years ago
- A GPT, made only of MLPs, in Jax☆57Updated 3 years ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆99Updated 2 years ago
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆54Updated 2 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 3 years ago
- An implementation of (Induced) Set Attention Block, from the Set Transformers paper☆56Updated 2 years ago
- ImageNet-12k subset of ImageNet-21k (fall11)☆21Updated last year
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆86Updated 3 years ago
- Implementation of Kronecker Attention in Pytorch☆18Updated 4 years ago
- Another attempt at a long-context / efficient transformer by me☆37Updated 3 years ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- A simple implementation of a deep linear Pytorch module☆19Updated 4 years ago
- JAX implementation ViT-VQGAN☆82Updated 2 years ago
- Code for ICLR 2021 Paper, "Anytime Sampling for Autoregressive Models via Ordered Autoencoding"☆26Updated last year
- Implementation of LogAvgExp for Pytorch☆35Updated 3 years ago
- ☆21Updated 2 years ago
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆57Updated last year
- ☆41Updated 2 years ago
- A convolution-free, transformer-only version of the CycleGAN framework☆33Updated 3 years ago
- ☆47Updated 2 years ago
- Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch☆52Updated 4 years ago
- This is a offical PyTorch/GPU implementation of SupMAE.☆77Updated 2 years ago
- Un-*** 50 billions multimodality dataset☆24Updated 2 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆48Updated 3 years ago
- Local Attention - Flax module for Jax☆20Updated 3 years ago
- AdaCat☆49Updated 2 years ago
- ☆33Updated 2 years ago
- ☆8Updated last year