MagedSaeed/generate-sequences

A python package made to generate sequences (greedy and beam-search) from Pytorch (not necessarily HF transformers) models.

46
/ 100
Emerging

This library helps deep learning practitioners generate text or sequences from their PyTorch models, even if they aren't Hugging Face compatible. It takes your custom PyTorch model and an input, then outputs the generated sequences using either greedy search or beam search decoding strategies. It's for machine learning engineers, researchers, and data scientists building custom sequence generation systems.

Available on PyPI.

Use this if you need to generate sequences (like text, code, or data streams) from a custom PyTorch deep learning model and want flexible control over the decoding process.

Not ideal if you are exclusively working with Hugging Face models, as their built-in generation methods are already optimized for their ecosystem.

deep-learning text-generation machine-translation sequence-modeling pytorch-development
Maintenance 6 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

18

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Dec 12, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/MagedSaeed/generate-sequences"

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