LiorSinai/TransformersLite.jl
A lightweight package for the transformer deep learning architecture in Julia
This package helps Julia programmers build custom deep learning models that understand context and generate sequences, like text or time series. It takes sequences of tokens (e.g., words represented as numbers) and produces classifications or new generated sequences based on transformer architecture components. This is ideal for machine learning engineers and researchers who need a lightweight, foundational toolkit for transformer-based applications.
No commits in the last 6 months.
Use this if you are a Julia programmer who wants to build, learn about, or customize transformer models from basic building blocks rather than using a high-level API.
Not ideal if you need ready-to-use, production-grade transformer models with extensive pre-trained options or integrations with large model hubs like HuggingFace.
Stars
43
Forks
1
Language
Julia
License
—
Category
Last pushed
Mar 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/LiorSinai/TransformersLite.jl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.