kyegomez/MambaDecoderBlock

MambaDecoderBlock is a novel decoder architecture that replaces traditional self-attention mechanisms with Mamba state space models, augmented by Mixture of Experts (MoE) layers.

31
/ 100
Emerging
No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

5

Forks

1

Language

Python

License

Apache-2.0

Category

3d-vision-transformers

Last pushed

Dec 02, 2025

Commits (30d)

0

GitHub
3D Vision Transformers · 83 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/MambaDecoderBlock"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

NVlabs/MambaVision

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

69

sign-language-translator/sign-language-translator

Python library & framework to build custom translators for the hearing-impaired and translate...

64

kyegomez/Jamba

PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"

56

fashn-AI/fashn-human-parser

Human parsing model for fashion and virtual try-on applications

55

autonomousvision/transfuser

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving;...

55

Explore Transformer Models

All categories Trending Transformer directory Insights