Doraemonzzz / xmixersLinks
Xmixers: A collection of SOTA efficient token/channel mixers
☆11Updated 6 months ago
Alternatives and similar repositories for xmixers
Users that are interested in xmixers are comparing it to the libraries listed below
Sorting:
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆15Updated last year
- [ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang☆14Updated last year
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆19Updated 10 months ago
- Official code for the paper "Attention as a Hypernetwork"☆36Updated 11 months ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆38Updated 3 weeks ago
- ☆23Updated 8 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated 9 months ago
- ☆54Updated 10 months ago
- Open-sourcing code associated with the AAAI-25 paper "On the Expressiveness and Length Generalization of Selective State-Space Models on …☆14Updated 3 weeks ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 11 months ago
- Here we will test various linear attention designs.☆58Updated last year
- Stick-breaking attention☆56Updated 2 months ago
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"☆32Updated last month
- DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)☆28Updated last month
- Flash-Linear-Attention models beyond language☆14Updated this week
- ☆31Updated last year
- ☆31Updated last year
- Official Code Repository for the paper "Key-value memory in the brain"☆26Updated 3 months ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19Updated 3 weeks ago
- ☆17Updated last month
- ☆14Updated 2 years ago
- ☆46Updated last year
- ☆20Updated last year
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆16Updated last month
- ☆21Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆64Updated last year
- Blog post☆17Updated last year
- Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…☆15Updated 2 months ago