kyegomez / MoE-Mamba
Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Zeta
☆102Updated 2 weeks ago
Alternatives and similar repositories for MoE-Mamba:
Users that are interested in MoE-Mamba are comparing it to the libraries listed below
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆166Updated 3 weeks ago
- A repository for DenseSSMs☆87Updated last year
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆52Updated 3 weeks ago
- Awesome list of papers that extend Mamba to various applications.☆132Updated 3 weeks ago
- Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta☆116Updated 3 weeks ago
- Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling☆192Updated 2 weeks ago
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆54Updated last year
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆218Updated 10 months ago
- Community Implementation of the paper: "Multi-Head Mixture-of-Experts" In PyTorch☆24Updated 2 weeks ago
- [ICLR 2025] Official Code Release for Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation☆42Updated last month
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆90Updated this week
- Simba☆206Updated last year
- Minimal Mamba-2 implementation in PyTorch☆188Updated 10 months ago
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆105Updated last year
- Code repository for Black Mamba☆245Updated last year
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆65Updated 4 months ago
- Notes on the Mamba and the S4 model (Mamba: Linear-Time Sequence Modeling with Selective State Spaces)☆162Updated last year
- An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivatio…☆85Updated last year
- ☆48Updated last year
- ☆57Updated 2 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆97Updated 6 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆85Updated 11 months ago
- Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficien…☆99Updated 3 weeks ago
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆128Updated 2 months ago
- Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆66Updated 9 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆214Updated last week
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆103Updated 7 months ago
- My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing o…☆43Updated 4 months ago
- ☆40Updated 2 months ago
- PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model …☆58Updated 5 months ago