kyegomez/MambaByte
Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta
This project offers an implementation of a 'MambaByte' model, which is a type of state-space model designed for processing various kinds of data without needing to break it into traditional 'tokens'. It takes raw, unstructured data as input and produces processed output from the model. This is intended for machine learning engineers or researchers who are working on developing high-performance artificial intelligence systems.
125 stars. Available on PyPI.
Use this if you are a machine learning engineer or researcher looking for a high-performance, token-free state-space model implementation for your deep learning projects.
Not ideal if you are an end-user without a strong background in deep learning model development or PyTorch.
Stars
125
Forks
9
Language
Python
License
MIT
Category
Last pushed
Feb 06, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/MambaByte"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
kyegomez/MambaTransformer
Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling
kyegomez/HSSS
Implementation of a Hierarchical Mamba as described in the paper: "Hierarchical State Space...
ghostperpper007/small_programming_model
A from-scratch Python code model with GNN-based structure encoding, Mamba-style SSM decoding,...