lucidrains / deep-cross-attention
Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch
☆81Updated last month
Alternatives and similar repositories for deep-cross-attention:
Users that are interested in deep-cross-attention are comparing it to the libraries listed below
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆82Updated 2 months ago
- Implementation of the proposed MaskBit from Bytedance AI☆75Updated 5 months ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆59Updated 2 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆103Updated 4 months ago
- Implementation of Agent Attention in Pytorch☆90Updated 9 months ago
- Implementation of a Light Recurrent Unit in Pytorch☆47Updated 6 months ago
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆34Updated 7 months ago
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆44Updated last month
- Implementation of a multimodal diffusion transformer in Pytorch☆101Updated 9 months ago
- Explorations into improving ViTArc with Slot Attention☆39Updated 5 months ago
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated 9 months ago
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆54Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆35Updated last month
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆152Updated last month
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆118Updated 6 months ago
- Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind☆47Updated 2 months ago
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆51Updated 2 months ago
- an implementation of FAdam (Fisher Adam) in PyTorch☆43Updated 10 months ago
- Triton implement of bi-directional (non-causal) linear attention☆46Updated 2 months ago
- A collection of tricks and tools to speed up transformer models☆152Updated 2 weeks ago
- More dimensions = More fun☆21Updated 8 months ago
- [ICLR 2025 Spotlight] Official Implementation for ToST (Token Statistics Transformer)☆80Updated last month
- Implementation of a modular, high-performance, and simplistic mamba for high-speed applications☆34Updated 5 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆27Updated 2 months ago
- Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch☆49Updated 4 months ago
- Minimal Implementation of Visual Autoregressive Modelling (VAR)☆29Updated 3 weeks ago
- Awesome list of papers that extend Mamba to various applications.☆132Updated last week
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆54Updated last week
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆64Updated 3 months ago
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆166Updated 2 weeks ago