State Space Model Python Packages

pyhgf

PyHGF: A neural network library for predictive coding

replay-trajectory-classification

State space models for decoding hippocampal trajectories and determining their type using sorted or clusterless data

replay-classification

State space models for categorization of replay content from multiunit spiking activity. Deng et al. 2016

unsupervised-multimodal-trajectory-modeling

We use EM for a mixture of state space models to perform unsupervised clustering of short trajectories.

long-range-models

Simple implementations of long-range sequence models (LRU, S5, S4, and more).

s0-tuning

Tune the initial recurrent state of hybrid models. Zero inference overhead.

dynaris

A JAX-powered library for state-space models

alloy-mlx

Hybrid SSM-Attention language model on Apple Silicon with MLX — interleaving Mamba-2 and Transformer for efficient inference

statecraft

Statecraft - Load, store and remix states for SSMs, Mamba and Stateful models