Doraemonzzz / tnn-pytorch
☆20Updated last year
Alternatives and similar repositories for tnn-pytorch:
Users that are interested in tnn-pytorch are comparing it to the libraries listed below
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆34Updated last year
- ☆33Updated last year
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19Updated last week
- [EMNLP 2023] Official implementation of the algorithm ETSC: Exact Toeplitz-to-SSM Conversion our EMNLP 2023 paper - Accelerating Toeplitz…☆14Updated last year
- ☆28Updated 8 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆64Updated 10 months ago
- ☆51Updated 8 months ago
- Blog post☆17Updated last year
- [ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling☆79Updated 10 months ago
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆33Updated 3 years ago
- ☆28Updated 4 months ago
- ☆13Updated 2 weeks ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆16Updated last year
- ☆51Updated 2 years ago
- HGRN2: Gated Linear RNNs with State Expansion☆53Updated 6 months ago
- ☆47Updated last year
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Updated 2 years ago
- Code for NeurIPS 2023 paper "Non-autoregressive Machine Translation with Probabilistic Context-free Grammar".☆11Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆25Updated 8 months ago
- ☆18Updated 9 months ago
- Efficient PScan implementation in PyTorch☆16Updated last year
- Code for the PAPA paper☆27Updated 2 years ago
- Official Code Repository for the paper "Key-value memory in the brain"☆23Updated 2 weeks ago
- ☆17Updated 8 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆61Updated 5 months ago
- ☆22Updated 3 years ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆25Updated 10 months ago
- sigma-MoE layer☆18Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆48Updated 2 years ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆36Updated last year