nanowell / Differential-Transformer-PyTorchLinks
PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture incorporates a novel Differential Attention mechanism, Multi-Head structure, RMSNorm, and SwiGLU.
☆73Updated 9 months ago
Alternatives and similar repositories for Differential-Transformer-PyTorch
Users that are interested in Differential-Transformer-PyTorch are comparing it to the libraries listed below
Sorting:
- Minimal Mamba-2 implementation in PyTorch☆216Updated last year
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆56Updated last week
- An open source community implementation of the model from "DIFFERENTIAL TRANSFORMER" paper by Microsoft.☆32Updated 2 weeks ago
- Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficien…☆116Updated last week
- Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling☆202Updated 2 weeks ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆226Updated last year
- Simba☆210Updated last year
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆74Updated 8 months ago
- State Space Models☆70Updated last year
- ☆47Updated last year
- ☆137Updated last year
- A repository for DenseSSMs☆88Updated last year
- ☆243Updated 5 months ago
- An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivatio…☆93Updated last year
- Awesome list of papers that extend Mamba to various applications.☆135Updated 2 months ago
- ☆72Updated 6 months ago
- ☆214Updated 6 months ago
- Implementation of xLSTM in Pytorch from the paper: "xLSTM: Extended Long Short-Term Memory"☆119Updated last week
- Offical implementation of "MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map" (NeurIPS2024 Oral)☆26Updated 7 months ago
- Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Ze…☆110Updated 2 weeks ago
- Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis☆249Updated last month
- Notes on the Mamba and the S4 model (Mamba: Linear-Time Sequence Modeling with Selective State Spaces)☆169Updated last year
- Official repository of MLLA (NeurIPS 2024)☆340Updated last month
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆183Updated last week
- ☆148Updated 11 months ago
- [Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications☆727Updated last month
- ☆196Updated last year
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆155Updated 6 months ago
- This is the implementation of Cross-attention inspired Mamba.☆33Updated 4 months ago
- Causal depthwise conv1d in CUDA, with a PyTorch interface☆552Updated this week