lucidrains / hyper-connections
Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public
☆77Updated last month
Alternatives and similar repositories for hyper-connections:
Users that are interested in hyper-connections are comparing it to the libraries listed below
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆101Updated 3 months ago
- Implementation of a Light Recurrent Unit in Pytorch☆47Updated 5 months ago
- Implementation of the proposed MaskBit from Bytedance AI☆75Updated 4 months ago
- Implementation of Agent Attention in Pytorch☆90Updated 8 months ago
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆42Updated this week
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 9 months ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆56Updated last month
- Implementation of Infini-Transformer in Pytorch☆109Updated 2 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆55Updated 10 months ago
- Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch☆81Updated last month
- Implementation of a multimodal diffusion transformer in Pytorch☆101Updated 9 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆120Updated 7 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆116Updated 5 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆98Updated 3 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆87Updated 4 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆95Updated 7 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆214Updated last month
- Focused on fast experimentation and simplicity☆69Updated 3 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆121Updated 7 months ago
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆57Updated last year
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆142Updated last week
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆63Updated last month
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆50Updated last month
- Explorations into improving ViTArc with Slot Attention☆39Updated 5 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆85Updated 10 months ago
- [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"☆76Updated last week
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆87Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆23Updated 2 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆44Updated 2 weeks ago
- Code accompanying the paper "Generalized Interpolating Discrete Diffusion"☆67Updated this week