lucidrains / coordinate-descent-attention
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
Alternatives and similar repositories for coordinate-descent-attention:
Users that are interested in coordinate-descent-attention are comparing it to the libraries listed below
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆57Updated last year
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆44Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 8 months ago
- Implementation of Tranception, an attention network, paired with retrieval, that is SOTA for protein fitness prediction☆31Updated 2 years ago
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆54Updated 2 years ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆50Updated last month
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆49Updated 9 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆118Updated 6 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆55Updated 11 months ago
- Implementation of a holodeck, written in Pytorch☆17Updated last year
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆34Updated 8 months ago
- ☆29Updated 2 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 Hourglass Transformer, in Pytorch, from Google and OpenAI☆87Updated 3 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 10 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 7 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆88Updated 5 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆24Updated 3 months ago
- Implementation of Insertion-deletion Denoising Diffusion Probabilistic Models☆30Updated 2 years ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆58Updated last week
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆103Updated 5 months ago
- Implementation of Infini-Transformer in Pytorch☆110Updated 4 months ago
- Experiment with diffusion models that you can run on your local jupyter instances☆59Updated 6 months ago
- Experimental scripts for researching data adaptive learning rate scheduling.☆23Updated last year
- ResiDual: Transformer with Dual Residual Connections, https://arxiv.org/abs/2304.14802☆93Updated last year
- ☆45Updated last year
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆57Updated last week
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆60Updated 3 years ago