s4
State space model library
This repository provides an implementation of structured state space sequence models using PyTorch
Structured state space sequence models
2k stars
52 watching
299 forks
Language: Jupyter Notebook
last commit: 8 months ago
Linked from 1 awesome list
pytorchsequence-modelsstate-space-models
filipecalegario/awesome-generative-aiRelated projects:
| Repository | Description | Stars |
|---|---|---|
 pasqal-io/pyqtorch | A PyTorch-based simulator for quantum machine learning | 45 |
 ibm/pytorch-seq2seq | A PyTorch-based framework for building and training sequence-to-sequence models | 1,499 |
 pytransitions/transitions | An object-oriented finite state machine implementation in Python with many extensions. | 5,822 |
 pytorch/torchtitan | A native PyTorch library for training large language models using distributed parallelism and optimization techniques. | 2,765 |
 qubvel-org/segmentation_models.pytorch | A comprehensive library for training and applying deep learning models for image segmentation | 9,829 |
 cornellius-gp/gpytorch | A library for creating scalable and flexible Gaussian process models with ease | 3,605 |
 eladhoffer/seq2seq.pytorch | Provides tools and frameworks for training sequence-to-sequence models using PyTorch | 523 |
 maximumentropy/seq2seq-pytorch | An implementation of Sequence to Sequence models in PyTorch with various attention mechanisms and extensions for machine translation tasks. | 738 |
 koz4k/dni-pytorch | Decoupled Neural Interfaces using Synthetic Gradients for PyTorch | 236 |
 knighton/torchplus | Enhances PyTorch modules by adding sequence step layers with implicit parentheses and supports custom activation functions. | 9 |
 pgularski/pysm | A versatile Python State Machine library for building flexible and scalable state-based systems | 73 |
 harvardnlp/pytorch-struct | A PyTorch library implementing differentiable structured prediction algorithms for deep learning applications. | 1,109 |
 kakaobrain/torchgpipe | A PyTorch-based library for efficient training of large neural networks using pipeline parallelism and automatic recomputation of gradients. | 820 |
 locuslab/tcn | An empirical evaluation of generic convolutional and recurrent networks for sequence modeling | 4,204 |
 ukplab/sentence-transformers | Provides dense vector representations for text using transformer networks | 15,556 |