Lucasc-99/NoTorch
A from-scratch neural network and transformers library, with speeds rivaling PyTorch
This is a neural network and transformer library built entirely from scratch using NumPy. It allows deep learning engineers and researchers to experiment with and build neural networks, processing raw data through custom architectures to produce trained models or predictions. It's for those who want to understand the underlying mechanics of deep learning frameworks or implement highly optimized custom operations.
No commits in the last 6 months.
Use this if you are a deep learning engineer or researcher interested in building neural networks and transformer models with a deep understanding of their low-level implementation, or if you need to integrate highly optimized custom operations where other frameworks might introduce overhead.
Not ideal if you are looking for a high-level, production-ready deep learning framework with extensive pre-built models and community support, as this project focuses on foundational implementation.
Stars
10
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Lucasc-99/NoTorch"
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