lucidrains / deep-cross-attentionLinks
Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch
☆88Updated 4 months ago
Alternatives and similar repositories for deep-cross-attention
Users that are interested in deep-cross-attention are comparing it to the libraries listed below
Sorting:
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆87Updated 3 weeks ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆65Updated last month
- Implementation of the proposed MaskBit from Bytedance AI☆82Updated 8 months ago
- Explorations into improving ViTArc with Slot Attention☆42Updated 8 months ago
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆34Updated this week
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆110Updated 7 months ago
- Implementation of Agent Attention in Pytorch☆90Updated last year
- Implementation of a multimodal diffusion transformer in Pytorch☆102Updated last year
- Autoregressive Image Generation☆32Updated last month
- an implementation of FAdam (Fisher Adam) in PyTorch☆47Updated 2 weeks ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 6 months ago
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆128Updated 2 weeks ago
- Implementation of a Light Recurrent Unit in Pytorch☆48Updated 9 months ago
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆37Updated 4 months ago
- Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch☆52Updated 7 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆119Updated 8 months ago
- Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.☆114Updated last month
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated last year
- Triton implement of bi-directional (non-causal) linear attention☆51Updated 5 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…☆49Updated 3 months ago
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆99Updated last year
- Implementation of a modular, high-performance, and simplistic mamba for high-speed applications☆36Updated 8 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆101Updated 8 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆175Updated last year
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆38Updated 3 months ago
- [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"☆115Updated last week
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆52Updated 5 months ago
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆36Updated 10 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 10 months ago