google/sequence-layers
A neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed layerwise (training) and stepwise (sampling).
This is a neural network API and library for machine learning engineers and researchers working on sequence models. It helps you design models that can process data both as a whole sequence (like for training) and one step at a time (like for real-time sampling). You define your model once, and it handles the complexities of running it in different modes, outputting a robust, deployable sequence model.
Available on PyPI.
Use this if you are a machine learning engineer or researcher building sequence models and need to easily switch between batch processing and real-time, step-by-step inference.
Not ideal if you are not a machine learning practitioner or developer and do not build neural networks.
Stars
56
Forks
13
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google/sequence-layers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
facebookresearch/fairseq2
FAIR Sequence Modeling Toolkit 2
lhotse-speech/lhotse
Tools for handling multimodal data in machine learning projects.
awslabs/sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
OpenNMT/OpenNMT-tf
Neural machine translation and sequence learning using TensorFlow
mozilla/translations
The code, training pipeline, and models that power Firefox Translations