tobna / TaylorShiftLinks
This repository contains the code for the paper "TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax"
☆13Updated 10 months ago
Alternatives and similar repositories for TaylorShift
Users that are interested in TaylorShift are comparing it to the libraries listed below
Sorting:
- A repository for DenseSSMs☆88Updated last year
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆122Updated last year
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Updated 2 years ago
- Implementation of Infini-Transformer in Pytorch☆112Updated last year
- Implementation of Agent Attention in Pytorch☆93Updated last year
- Code for the paper "Cottention: Linear Transformers With Cosine Attention"☆20Updated 2 months ago
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆40Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆56Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆106Updated 2 years ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆102Updated last year
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆28Updated 9 months ago
- Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Ze…☆120Updated last week
- Implementation of a modular, high-performance, and simplistic mamba for high-speed applications☆40Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆41Updated last month
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆58Updated last year
- ☆48Updated last year
- Explorations into improving ViTArc with Slot Attention☆43Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆168Updated 3 weeks ago
- The open source implementation of the multi grouped query attention by the paper "GQA: Training Generalized Multi-Query Transformer Model…☆15Updated 2 years ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆137Updated last month
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆57Updated last year
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆114Updated last week
- Implementation of a Light Recurrent Unit in Pytorch☆49Updated last year
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆56Updated 3 months ago
- The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".☆18Updated 9 months ago
- Autoregressive Image Generation☆31Updated 7 months ago
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆41Updated last year
- DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)☆32Updated 10 months ago
- ☆36Updated 10 months ago