OpenNLPLab / HGRNLinks
[NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Sequence Modeling
☆66Updated last year
Alternatives and similar repositories for HGRN
Users that are interested in HGRN are comparing it to the libraries listed below
Sorting:
- ☆49Updated last year
- ☆56Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆27Updated last year
- ☆19Updated 2 years ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated 11 months ago
- [ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling☆79Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- Randomized Positional Encodings Boost Length Generalization of Transformers☆82Updated last year
- ☆32Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- ☆51Updated 2 years ago
- ☆33Updated last year
- Efficient PScan implementation in PyTorch☆16Updated last year
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆46Updated 2 months ago
- ☆23Updated 10 months ago
- ☆33Updated 9 months ago
- ☆37Updated last year
- [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"☆118Updated 3 weeks ago
- ☆106Updated last year
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19Updated 2 months ago
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆23Updated 3 months ago
- ☆88Updated last year
- Jax implementation of "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆14Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Stick-breaking attention☆58Updated last month
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆53Updated 2 years ago
- Experiments on the impact of depth in transformers and SSMs.☆32Updated 8 months ago
- DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)☆28Updated 3 months ago
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆54Updated 8 months ago