Itamarzimm / UnifiedImplicitAttnReprLinks
[ICLR 2025] Official Code Release for Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
☆42Updated 3 months ago
Alternatives and similar repositories for UnifiedImplicitAttnRepr
Users that are interested in UnifiedImplicitAttnRepr are comparing it to the libraries listed below
Sorting:
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆54Updated 11 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated 9 months ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆222Updated last year
- DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)☆28Updated last month
- A repository for DenseSSMs☆87Updated last year
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆68Updated 5 months ago
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆17Updated last month
- Here we will test various linear attention designs.☆58Updated last year
- Implementation of MambaFormer in Pytorch ++ Zeta from the paper: "Can Mamba Learn How to Learn? A Comparative Study on In-Context Learnin…☆21Updated last week
- ☆61Updated 4 months ago
- My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing o…☆43Updated 5 months ago
- ☆48Updated last year
- Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆67Updated 10 months ago
- ☆43Updated 4 months ago
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆55Updated 2 months ago
- ☆23Updated 8 months ago
- Triton implement of bi-directional (non-causal) linear attention☆49Updated 4 months ago
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆137Updated 4 months ago
- Code for the paper "Cottention: Linear Transformers With Cosine Attention"☆17Updated 7 months ago
- ☆54Updated 10 months ago
- Official code for the paper "Attention as a Hypernetwork"☆36Updated 11 months ago
- PyTorch implementation of "From Sparse to Soft Mixtures of Experts"☆57Updated last year
- Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Ze…☆105Updated 2 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆64Updated last year
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆38Updated 7 months ago
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆22Updated 6 months ago
- ☆104Updated last year
- ☆79Updated 9 months ago
- ☆28Updated 7 months ago
- Implementation of the model "Hedgehog" from the paper: "The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry"☆13Updated last year