moskomule/simple_transformers
Simple transformer implementations that I can understand
This project helps machine learning researchers and students understand and experiment with core transformer architectures for language and image tasks. It takes raw text datasets like Wikitext or image datasets like ImageNet as input, and outputs trained GPT, Vision Transformer (ViT), or CaiT models. This is for individuals building or evaluating foundational AI models.
No commits in the last 6 months.
Use this if you are a researcher or student who wants to grasp the fundamental mechanics of transformer models for language modeling or image classification through clear, simplified implementations.
Not ideal if you need a production-ready, highly optimized library with a vast array of pre-trained models and advanced features for immediate application.
Stars
20
Forks
1
Language
Python
License
—
Category
Last pushed
Dec 28, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/moskomule/simple_transformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action